diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
index e9d63d83b..086bb2e43 100644
--- a/ARCHITECTURE.md
+++ b/ARCHITECTURE.md
@@ -217,7 +217,7 @@ Every skill starts with a `{{PREAMBLE}}` block that runs before the skill's own
 
 1. **Update check** — calls `gstack-update-check`, reports if an upgrade is available.
 2. **Session tracking** — touches `~/.gstack/sessions/$PPID` and counts active sessions (files modified in the last 2 hours). When 3+ sessions are running, all skills enter "ELI16 mode" — every question re-grounds the user on context because they're juggling windows.
-3. **Contributor mode** — reads `gstack_contributor` from config. When true, the agent files casual field reports to `~/.gstack/contributor-logs/` when gstack itself misbehaves.
+3. **Operational self-improvement** — at the end of every skill session, the agent reflects on failures (CLI errors, wrong approaches, project quirks) and logs operational learnings to the project's JSONL file for future sessions.
 4. **AskUserQuestion format** — universal format: context, question, `RECOMMENDATION: Choose X because ___`, lettered options. Consistent across all skills.
 5. **Search Before Building** — before building infrastructure or unfamiliar patterns, search first. Three layers of knowledge: tried-and-true (Layer 1), new-and-popular (Layer 2), first-principles (Layer 3). When first-principles reasoning reveals conventional wisdom is wrong, the agent names the "eureka moment" and logs it. See `ETHOS.md` for the full builder philosophy.
 
diff --git a/CHANGELOG.md b/CHANGELOG.md
index e61d3f02b..9fb64b3a0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,23 @@
 # Changelog
 
+## [0.13.10.0] - 2026-03-29 — Recursive Self-Improvement
+
+gstack now learns from its own mistakes. Every skill session captures operational failures (CLI errors, wrong approaches, project quirks) and surfaces them in future sessions. No setup needed, just works.
+
+### Added
+
+- **Operational self-improvement.** When a command fails or you hit a project-specific gotcha, gstack logs it. Next session, it remembers. "bun test needs --timeout 30000" or "login flow requires cookie import first" ... the kind of stuff that wastes 10 minutes every time you forget it.
+- **Learnings summary in preamble.** When your project has 5+ learnings, gstack shows the top 3 at the start of every session so you see them before you start working.
+- **13 skills now learn.** office-hours, plan-ceo-review, plan-eng-review, plan-design-review, design-review, design-consultation, cso, qa, qa-only, and retro all now read prior learnings AND contribute new ones. Previously only review, ship, and investigate were wired.
+
+### Changed
+
+- **Contributor mode replaced.** The old contributor mode (manual opt-in, markdown reports to ~/.gstack/contributor-logs/) never fired in 18 days of heavy use. Replaced with automatic operational learning that captures the same insights without any setup.
+
+### Fixed
+
+- **learnings-show E2E test slug mismatch.** The test seeded learnings at a hardcoded path but gstack-slug computed a different path at runtime. Now computes the slug dynamically.
+
 ## [0.13.9.0] - 2026-03-29 — Composable Skills
 
 Skills can now load other skills inline. Write `{{INVOKE_SKILL:office-hours}}` in a template and the generator emits the right "read file, skip preamble, follow instructions" prose automatically. Handles host-aware paths and customizable skip lists.
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index b6dba47cd..fcb9c279a 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -20,26 +20,19 @@ Now edit any `SKILL.md`, invoke it in Claude Code (e.g. `/review`), and see your
 bin/dev-teardown               # deactivate — back to your global install
 ```
 
-## Contributor mode
+## Operational self-improvement
 
-Contributor mode turns gstack into a self-improving tool. Enable it and Claude Code
-will periodically reflect on its gstack experience — rating it 0-10 at the end of
-each major workflow step. When something isn't a 10, it thinks about why and files
-a report to `~/.gstack/contributor-logs/` with what happened, repro steps, and what
-would make it better.
+gstack automatically learns from failures. At the end of every skill session, the agent
+reflects on what went wrong (CLI errors, wrong approaches, project quirks) and logs
+operational learnings to `~/.gstack/projects/{slug}/learnings.jsonl`. Future sessions
+surface these learnings automatically, so gstack gets smarter on your codebase over time.
 
-```bash
-~/.claude/skills/gstack/bin/gstack-config set gstack_contributor true
-```
-
-The logs are for **you**. When something bugs you enough to fix, the report is
-already written. Fork gstack, symlink your fork into the project where you hit
-the issue, fix it, and open a PR.
+No setup needed. Learnings are logged automatically. View them with `/learn`.
 
 ### The contributor workflow
 
-1. **Use gstack normally** — contributor mode reflects and logs issues automatically
-2. **Check your logs:** `ls ~/.gstack/contributor-logs/`
+1. **Use gstack normally** — operational learnings are captured automatically
+2. **Check your learnings:** `/learn` or `ls ~/.gstack/projects/*/learnings.jsonl`
 3. **Fork and clone gstack** (if you haven't already)
 4. **Symlink your fork into the project where you hit the bug:**
    ```bash
diff --git a/SKILL.md b/SKILL.md
index e0e6ccca7..a57c7aab9 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -25,7 +25,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -46,8 +45,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"gstack","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"gstack","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -65,6 +64,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -208,24 +210,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -251,6 +235,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -269,22 +271,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/VERSION b/VERSION
index 1ef377f37..c1f7a09af 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-0.13.9.0
+0.13.10.0
diff --git a/autoplan/SKILL.md b/autoplan/SKILL.md
index 2754cef07..b0fe1cf22 100644
--- a/autoplan/SKILL.md
+++ b/autoplan/SKILL.md
@@ -34,7 +34,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -55,8 +54,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"autoplan","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"autoplan","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -74,6 +73,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -300,24 +302,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -343,6 +327,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -361,22 +363,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -683,7 +685,6 @@ Read each file using the Read tool:
 - AskUserQuestion Format
 - Completeness Principle — Boil the Lake
 - Search Before Building
-- Contributor Mode
 - Completion Status Protocol
 - Telemetry (run last)
 - Step 0: Detect base branch
diff --git a/autoplan/SKILL.md.tmpl b/autoplan/SKILL.md.tmpl
index 38ab2816e..41a1d4b34 100644
--- a/autoplan/SKILL.md.tmpl
+++ b/autoplan/SKILL.md.tmpl
@@ -202,7 +202,6 @@ Read each file using the Read tool:
 - AskUserQuestion Format
 - Completeness Principle — Boil the Lake
 - Search Before Building
-- Contributor Mode
 - Completion Status Protocol
 - Telemetry (run last)
 - Step 0: Detect base branch
diff --git a/benchmark/SKILL.md b/benchmark/SKILL.md
index 8fe4bc94c..21094430e 100644
--- a/benchmark/SKILL.md
+++ b/benchmark/SKILL.md
@@ -27,7 +27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -48,8 +47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"benchmark","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -67,6 +66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -210,24 +212,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -253,6 +237,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -271,22 +273,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/browse/SKILL.md b/browse/SKILL.md
index 6cec51b74..f96d749dd 100644
--- a/browse/SKILL.md
+++ b/browse/SKILL.md
@@ -27,7 +27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -48,8 +47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"browse","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -67,6 +66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -210,24 +212,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -253,6 +237,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -271,22 +273,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/canary/SKILL.md b/canary/SKILL.md
index 6197b3c42..d4b589f7d 100644
--- a/canary/SKILL.md
+++ b/canary/SKILL.md
@@ -27,7 +27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -48,8 +47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"canary","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"canary","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -67,6 +66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -275,24 +277,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -318,6 +302,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -336,22 +338,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/codex/SKILL.md b/codex/SKILL.md
index a3eb12cf3..f42e63551 100644
--- a/codex/SKILL.md
+++ b/codex/SKILL.md
@@ -28,7 +28,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -49,8 +48,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"codex","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"codex","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -68,6 +67,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -294,24 +296,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -337,6 +321,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -355,22 +357,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/connect-chrome/SKILL.md b/connect-chrome/SKILL.md
index c863b171f..b167a113f 100644
--- a/connect-chrome/SKILL.md
+++ b/connect-chrome/SKILL.md
@@ -25,7 +25,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -46,8 +45,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"connect-chrome","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"connect-chrome","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -65,6 +64,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -291,24 +293,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -334,6 +318,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -352,22 +354,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/cso/SKILL.md b/cso/SKILL.md
index 3945884cf..cd037fe7d 100644
--- a/cso/SKILL.md
+++ b/cso/SKILL.md
@@ -31,7 +31,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -52,8 +51,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"cso","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -71,6 +70,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -279,24 +281,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -322,6 +306,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -340,22 +342,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -473,6 +475,44 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel"
 
 This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings.
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Phase 1: Attack Surface Census
 
 Map what an attacker sees — both code surface and infrastructure surface.
@@ -992,6 +1032,31 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch
 
 If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"cso","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.
diff --git a/cso/SKILL.md.tmpl b/cso/SKILL.md.tmpl
index 120319f65..b4e9f7bfe 100644
--- a/cso/SKILL.md.tmpl
+++ b/cso/SKILL.md.tmpl
@@ -102,6 +102,8 @@ grep -q "laravel" composer.json 2>/dev/null && echo "FRAMEWORK: Laravel"
 
 This is NOT a checklist — it's a reasoning phase. The output is understanding, not findings.
 
+{{LEARNINGS_SEARCH}}
+
 ### Phase 1: Attack Surface Census
 
 Map what an attacker sees — both code surface and infrastructure surface.
@@ -598,6 +600,8 @@ Write findings to `.gstack/security-reports/{date}-{HHMMSS}.json` using this sch
 
 If `.gstack/` is not in `.gitignore`, note it in findings — security reports should stay local.
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.
diff --git a/design-consultation/SKILL.md b/design-consultation/SKILL.md
index 3901ada1d..3695fdbc4 100644
--- a/design-consultation/SKILL.md
+++ b/design-consultation/SKILL.md
@@ -32,7 +32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -53,8 +52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-consultation","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-consultation","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -72,6 +71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -298,24 +300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -341,6 +325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -359,22 +361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -543,6 +545,44 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Phase 1: Product Context
 
 Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase.
@@ -1026,6 +1066,31 @@ List all decisions. Flag any that used agent defaults without explicit user conf
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"design-consultation","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.
diff --git a/design-consultation/SKILL.md.tmpl b/design-consultation/SKILL.md.tmpl
index 5f46317c8..4b23fa60c 100644
--- a/design-consultation/SKILL.md.tmpl
+++ b/design-consultation/SKILL.md.tmpl
@@ -79,6 +79,8 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Phase 1: Product Context
 
 Ask the user a single question that covers everything you need to know. Pre-fill what you can infer from the codebase.
@@ -415,6 +417,8 @@ List all decisions. Flag any that used agent defaults without explicit user conf
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.
diff --git a/design-review/SKILL.md b/design-review/SKILL.md
index c152835c7..cc4cf1cce 100644
--- a/design-review/SKILL.md
+++ b/design-review/SKILL.md
@@ -32,7 +32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -53,8 +52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -72,6 +71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -298,24 +300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -341,6 +325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -359,22 +361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -713,6 +715,44 @@ echo "REPORT_DIR: $REPORT_DIR"
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Phases 1-6: Design Audit Baseline
 
 ## Modes
@@ -1379,6 +1419,31 @@ If the repo has a `TODOS.md`:
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"design-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (design-review specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
diff --git a/design-review/SKILL.md.tmpl b/design-review/SKILL.md.tmpl
index de57c217b..adca09913 100644
--- a/design-review/SKILL.md.tmpl
+++ b/design-review/SKILL.md.tmpl
@@ -97,6 +97,8 @@ echo "REPORT_DIR: $REPORT_DIR"
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Phases 1-6: Design Audit Baseline
 
 {{DESIGN_METHODOLOGY}}
@@ -287,6 +289,8 @@ If the repo has a `TODOS.md`:
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (design-review specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
diff --git a/design-shotgun/SKILL.md b/design-shotgun/SKILL.md
index 609907d60..cb091b390 100644
--- a/design-shotgun/SKILL.md
+++ b/design-shotgun/SKILL.md
@@ -29,7 +29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -50,8 +49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"design-shotgun","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"design-shotgun","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -69,6 +68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -277,24 +279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -320,6 +304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -338,22 +340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/document-release/SKILL.md b/document-release/SKILL.md
index a1c6ede92..10df26898 100644
--- a/document-release/SKILL.md
+++ b/document-release/SKILL.md
@@ -29,7 +29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -50,8 +49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"document-release","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"document-release","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -69,6 +68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -277,24 +279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -320,6 +304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -338,22 +340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -516,7 +518,7 @@ Read each documentation file and cross-reference it against the diff. Use these
 - Walk through the setup instructions as if you are a brand new contributor.
 - Are the listed commands accurate? Would each step succeed?
 - Do test tier descriptions match the current test infrastructure?
-- Are workflow descriptions (dev setup, contributor mode, etc.) current?
+- Are workflow descriptions (dev setup, operational learnings, etc.) current?
 - Flag anything that would fail or confuse a first-time contributor.
 
 **CLAUDE.md / project instructions:**
diff --git a/document-release/SKILL.md.tmpl b/document-release/SKILL.md.tmpl
index b1b6f684a..4285525c2 100644
--- a/document-release/SKILL.md.tmpl
+++ b/document-release/SKILL.md.tmpl
@@ -108,7 +108,7 @@ Read each documentation file and cross-reference it against the diff. Use these
 - Walk through the setup instructions as if you are a brand new contributor.
 - Are the listed commands accurate? Would each step succeed?
 - Do test tier descriptions match the current test infrastructure?
-- Are workflow descriptions (dev setup, contributor mode, etc.) current?
+- Are workflow descriptions (dev setup, operational learnings, etc.) current?
 - Flag anything that would fail or confuse a first-time contributor.
 
 **CLAUDE.md / project instructions:**
diff --git a/investigate/SKILL.md b/investigate/SKILL.md
index ab940d175..771cd814d 100644
--- a/investigate/SKILL.md
+++ b/investigate/SKILL.md
@@ -44,7 +44,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -65,8 +64,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"investigate","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"investigate","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -84,6 +83,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -292,24 +294,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -335,6 +319,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -353,22 +355,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -603,7 +605,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
diff --git a/land-and-deploy/SKILL.md b/land-and-deploy/SKILL.md
index 6311ecfc7..d705b4b03 100644
--- a/land-and-deploy/SKILL.md
+++ b/land-and-deploy/SKILL.md
@@ -26,7 +26,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -47,8 +46,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"land-and-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"land-and-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -66,6 +65,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -292,24 +294,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -335,6 +319,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -353,22 +355,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/learn/SKILL.md b/learn/SKILL.md
index 324b4a387..6d3a5b377 100644
--- a/learn/SKILL.md
+++ b/learn/SKILL.md
@@ -29,7 +29,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -50,8 +49,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"learn","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"learn","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -69,6 +68,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -277,24 +279,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -320,6 +304,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -338,22 +340,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/office-hours/SKILL.md b/office-hours/SKILL.md
index 75beef32c..e592a1aeb 100644
--- a/office-hours/SKILL.md
+++ b/office-hours/SKILL.md
@@ -36,7 +36,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -57,8 +56,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"office-hours","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"office-hours","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -76,6 +75,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -302,24 +304,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -345,6 +329,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -363,22 +365,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -1421,6 +1423,31 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"office-hours","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Important Rules
 
 - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding.
diff --git a/office-hours/SKILL.md.tmpl b/office-hours/SKILL.md.tmpl
index ba7c3c1e5..9fd6b9024 100644
--- a/office-hours/SKILL.md.tmpl
+++ b/office-hours/SKILL.md.tmpl
@@ -644,6 +644,8 @@ The design doc at `~/.gstack/projects/` is automatically discoverable by downstr
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Important Rules
 
 - **Never start implementation.** This skill produces design docs, not code. Not even scaffolding.
diff --git a/package.json b/package.json
index f34218c07..bc6747fcc 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "gstack",
-  "version": "0.13.9.0",
+  "version": "0.13.10.0",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",
diff --git a/plan-ceo-review/SKILL.md b/plan-ceo-review/SKILL.md
index c76316693..334b8b389 100644
--- a/plan-ceo-review/SKILL.md
+++ b/plan-ceo-review/SKILL.md
@@ -32,7 +32,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -53,8 +52,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-ceo-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-ceo-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -72,6 +71,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -298,24 +300,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -341,6 +325,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -359,22 +361,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -1619,6 +1621,31 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th
 * After each section, pause and wait for feedback.
 * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-ceo-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Mode Quick Reference
 ```
   ┌────────────────────────────────────────────────────────────────────────────────┐
diff --git a/plan-ceo-review/SKILL.md.tmpl b/plan-ceo-review/SKILL.md.tmpl
index b33aaa30c..319c3c1a7 100644
--- a/plan-ceo-review/SKILL.md.tmpl
+++ b/plan-ceo-review/SKILL.md.tmpl
@@ -779,6 +779,8 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th
 * After each section, pause and wait for feedback.
 * Use **CRITICAL GAP** / **WARNING** / **OK** for scannability.
 
+{{LEARNINGS_LOG}}
+
 ## Mode Quick Reference
 ```
   ┌────────────────────────────────────────────────────────────────────────────────┐
diff --git a/plan-design-review/SKILL.md b/plan-design-review/SKILL.md
index 86a950a84..74c97c261 100644
--- a/plan-design-review/SKILL.md
+++ b/plan-design-review/SKILL.md
@@ -30,7 +30,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -51,8 +50,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-design-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -70,6 +69,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -296,24 +298,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -339,6 +323,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -357,22 +359,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -913,6 +915,44 @@ descriptions of what 10/10 looks like.
 
 ## Review Sections (7 passes, after scope is agreed)
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Pass 1: Information Architecture
 Rate 0-10: Does the plan define what the user sees first, second, third?
 FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3?
@@ -1268,6 +1308,31 @@ plan's living status.
 - Always place it as the very last section in the plan file. If it was found mid-file,
   move it: delete the old location and append at the end.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-design-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale.
diff --git a/plan-design-review/SKILL.md.tmpl b/plan-design-review/SKILL.md.tmpl
index 2edfe3795..9367ee27d 100644
--- a/plan-design-review/SKILL.md.tmpl
+++ b/plan-design-review/SKILL.md.tmpl
@@ -257,6 +257,8 @@ descriptions of what 10/10 looks like.
 
 ## Review Sections (7 passes, after scope is agreed)
 
+{{LEARNINGS_SEARCH}}
+
 ### Pass 1: Information Architecture
 Rate 0-10: Does the plan define what the user sees first, second, third?
 FIX TO 10: Add information hierarchy to the plan. Include ASCII diagram of screen/page structure and navigation flow. Apply "constraint worship" — if you can only show 3 things, which 3?
@@ -431,6 +433,8 @@ Substitute values from the Completion Summary:
 
 {{PLAN_FILE_REVIEW_REPORT}}
 
+{{LEARNINGS_LOG}}
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, recommend the next review(s) based on what this design review discovered. Read the dashboard output to see which reviews have already been run and whether they are stale.
diff --git a/plan-eng-review/SKILL.md b/plan-eng-review/SKILL.md
index 1dad9fc0b..5684d877c 100644
--- a/plan-eng-review/SKILL.md
+++ b/plan-eng-review/SKILL.md
@@ -31,7 +31,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -52,8 +51,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"plan-eng-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-eng-review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -71,6 +70,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -297,24 +299,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -340,6 +324,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -358,22 +360,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -1231,6 +1233,31 @@ plan's living status.
 - Always place it as the very last section in the plan file. If it was found mid-file,
   move it: delete the old location and append at the end.
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"plan-eng-review","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.
diff --git a/plan-eng-review/SKILL.md.tmpl b/plan-eng-review/SKILL.md.tmpl
index f15fc7f58..fca7535ef 100644
--- a/plan-eng-review/SKILL.md.tmpl
+++ b/plan-eng-review/SKILL.md.tmpl
@@ -287,6 +287,8 @@ Substitute values from the Completion Summary:
 
 {{PLAN_FILE_REVIEW_REPORT}}
 
+{{LEARNINGS_LOG}}
+
 ## Next Steps — Review Chaining
 
 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.
diff --git a/qa-only/SKILL.md b/qa-only/SKILL.md
index 2beb599a5..58e110fb7 100644
--- a/qa-only/SKILL.md
+++ b/qa-only/SKILL.md
@@ -27,7 +27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -48,8 +47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"qa-only","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"qa-only","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -67,6 +66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -293,24 +295,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -336,6 +320,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -354,22 +356,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -472,6 +474,44 @@ mkdir -p "$REPORT_DIR/screenshots"
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:
@@ -796,6 +836,31 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md`
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"qa-only","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (qa-only specific)
 
 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop.
diff --git a/qa-only/SKILL.md.tmpl b/qa-only/SKILL.md.tmpl
index d9fc96585..1aea67e0b 100644
--- a/qa-only/SKILL.md.tmpl
+++ b/qa-only/SKILL.md.tmpl
@@ -49,6 +49,8 @@ mkdir -p "$REPORT_DIR/screenshots"
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:
@@ -97,6 +99,8 @@ Report filenames use the domain and date: `qa-report-myapp-com-2026-03-12.md`
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (qa-only specific)
 
 11. **Never fix bugs.** Find and document only. Do not read source code, edit files, or suggest fixes in the report. Your job is to report what's broken, not to fix it. Use `/qa` for the test-fix-verify loop.
diff --git a/qa/SKILL.md b/qa/SKILL.md
index 94081f20e..eb38c15ea 100644
--- a/qa/SKILL.md
+++ b/qa/SKILL.md
@@ -33,7 +33,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -54,8 +53,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"qa","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"qa","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -73,6 +72,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -299,24 +301,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -342,6 +326,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -360,22 +362,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -702,6 +704,44 @@ mkdir -p .gstack/qa-reports/screenshots
 
 ---
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:
@@ -1203,6 +1243,31 @@ If the repo has a `TODOS.md`:
 
 ---
 
+## Capture Learnings
+
+If you discovered a non-obvious pattern, pitfall, or architectural insight during
+this session, log it for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"qa","type":"TYPE","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"SOURCE","files":["path/to/relevant/file"]}'
+```
+
+**Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
+
+**Sources:** `observed` (you found this in the code), `user-stated` (user told you),
+`inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
+
+**Confidence:** 1-10. Be honest. An observed pattern you verified in the code is 8-9.
+An inference you're not sure about is 4-5. A user preference they explicitly stated is 10.
+
+**files:** Include the specific file paths this learning references. This enables
+staleness detection: if those files are later deleted, the learning can be flagged.
+
+**Only log genuine discoveries.** Don't log obvious things. Don't log things the user
+already knows. A good test: would this insight save time in a future session? If yes, log it.
+
 ## Additional Rules (qa-specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
diff --git a/qa/SKILL.md.tmpl b/qa/SKILL.md.tmpl
index 20f70ef94..697853953 100644
--- a/qa/SKILL.md.tmpl
+++ b/qa/SKILL.md.tmpl
@@ -90,6 +90,8 @@ mkdir -p .gstack/qa-reports/screenshots
 
 ---
 
+{{LEARNINGS_SEARCH}}
+
 ## Test Plan Context
 
 Before falling back to git diff heuristics, check for richer test plan sources:
@@ -315,6 +317,8 @@ If the repo has a `TODOS.md`:
 
 ---
 
+{{LEARNINGS_LOG}}
+
 ## Additional Rules (qa-specific)
 
 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
diff --git a/retro/SKILL.md b/retro/SKILL.md
index 5a84039b1..d0202546b 100644
--- a/retro/SKILL.md
+++ b/retro/SKILL.md
@@ -27,7 +27,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -48,8 +47,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"retro","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"retro","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -67,6 +66,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -275,24 +277,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -318,6 +302,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -336,22 +338,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -466,6 +468,44 @@ Usage: /retro [window | compare | global]
 
 **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo.
 
+## Prior Learnings
+
+Search for relevant learnings from previous sessions:
+
+```bash
+_CROSS_PROJ=$(~/.claude/skills/gstack/bin/gstack-config get cross_project_learnings 2>/dev/null || echo "unset")
+echo "CROSS_PROJECT: $_CROSS_PROJ"
+if [ "$_CROSS_PROJ" = "true" ]; then
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 --cross-project 2>/dev/null || true
+else
+  ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 10 2>/dev/null || true
+fi
+```
+
+If `CROSS_PROJECT` is `unset` (first time): Use AskUserQuestion:
+
+> gstack can search learnings from your other projects on this machine to find
+> patterns that might apply here. This stays local (no data leaves your machine).
+> Recommended for solo developers. Skip if you work on multiple client codebases
+> where cross-contamination would be a concern.
+
+Options:
+- A) Enable cross-project learnings (recommended)
+- B) Keep learnings project-scoped only
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set cross_project_learnings false`
+
+Then re-run the search with the appropriate flag.
+
+If learnings are found, incorporate them into your analysis. When a review finding
+matches a past learning, display:
+
+**"Prior learning applied: [key] (confidence N/10, from [date])"**
+
+This makes the compounding visible. The user should see that gstack is getting
+smarter on their codebase over time.
+
 ### Step 1: Gather Raw Data
 
 First, fetch origin and identify the current user:
@@ -695,7 +735,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
diff --git a/retro/SKILL.md.tmpl b/retro/SKILL.md.tmpl
index 5b201cf66..d89cb7175 100644
--- a/retro/SKILL.md.tmpl
+++ b/retro/SKILL.md.tmpl
@@ -58,6 +58,8 @@ Usage: /retro [window | compare | global]
 
 **If the first argument is `global`:** Skip the normal repo-scoped retro (Steps 1-14). Instead, follow the **Global Retrospective** flow at the end of this document. The optional second argument is the time window (default 7d). This mode does NOT require being inside a git repo.
 
+{{LEARNINGS_SEARCH}}
+
 ### Step 1: Gather Raw Data
 
 First, fetch origin and identify the current user:
diff --git a/review/SKILL.md b/review/SKILL.md
index 3f492d21f..2b5b61941 100644
--- a/review/SKILL.md
+++ b/review/SKILL.md
@@ -30,7 +30,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -51,8 +50,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"review","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -70,6 +69,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -296,24 +298,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -339,6 +323,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -357,22 +359,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -1264,7 +1266,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
diff --git a/scripts/resolvers/learnings.ts b/scripts/resolvers/learnings.ts
index 3bcba7b1f..685188fb2 100644
--- a/scripts/resolvers/learnings.ts
+++ b/scripts/resolvers/learnings.ts
@@ -80,7 +80,8 @@ ${binDir}/gstack-learnings-log '{"skill":"${ctx.skillName}","type":"TYPE","key":
 \`\`\`
 
 **Types:** \`pattern\` (reusable approach), \`pitfall\` (what NOT to do), \`preference\`
-(user stated), \`architecture\` (structural decision), \`tool\` (library/framework insight).
+(user stated), \`architecture\` (structural decision), \`tool\` (library/framework insight),
+\`operational\` (project environment/CLI/workflow knowledge).
 
 **Sources:** \`observed\` (you found this in the code), \`user-stated\` (user told you),
 \`inferred\` (AI deduction), \`cross-model\` (both Claude and Codex agree).
diff --git a/scripts/resolvers/preamble.ts b/scripts/resolvers/preamble.ts
index 8cd1b5572..0e759023b 100644
--- a/scripts/resolvers/preamble.ts
+++ b/scripts/resolvers/preamble.ts
@@ -8,9 +8,8 @@ import type { TemplateContext } from './types';
  * repo mode detection, and telemetry.
  *
  * Telemetry data flow:
- *   1. If _TEL != "off": local JSONL append to ~/.gstack/analytics/ (inline, inspectable)
+ *   1. Always: local JSONL append to ~/.gstack/analytics/ (inline, inspectable)
  *   2. If _TEL != "off" AND binary exists: gstack-telemetry-log for remote reporting
- *   When telemetry is off, nothing is written anywhere. Clean trust contract.
  */
 
 function generatePreambleBash(ctx: TemplateContext): string {
@@ -34,7 +33,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(${ctx.paths.binDir}/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(${ctx.paths.binDir}/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -55,8 +53,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: \${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "\${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -74,6 +72,9 @@ _LEARN_FILE="\${GSTACK_HOME:-$HOME/.gstack}/projects/\${SLUG:-unknown}/learnings
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ${ctx.paths.binDir}/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -379,27 +380,7 @@ jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg b
 \`\`\``;
 }
 
-function generateContributorMode(): string {
-  return `## Contributor Mode
-
-If \`_CONTRIB\` is \`true\`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write \`~/.gstack/contributor-logs/{slug}.md\`:
-\`\`\`
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-\`\`\`
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.`;
-}
-
-function generateCompletionStatus(): string {
+function generateCompletionStatus(ctx: TemplateContext): string {
   return `## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -425,6 +406,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 \`\`\`
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+\`\`\`bash
+${ctx.paths.binDir}/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+\`\`\`
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -443,22 +442,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \\
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \\
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \\
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \\
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 \`\`\`
 
 Replace \`SKILL_NAME\` with the actual skill name from frontmatter, \`OUTCOME\` with
 success/error/abort, and \`USED_BROWSE\` with true/false based on whether \`$B\` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -557,7 +556,7 @@ Avoid filler, throat-clearing, generic optimism, founder cosplay, and unsupporte
 
 // Preamble Composition (tier → sections)
 // ─────────────────────────────────────────────
-// T1: core + upgrade + lake + telemetry + voice(trimmed) + contributor + completion
+// T1: core + upgrade + lake + telemetry + voice(trimmed) + completion
 // T2: T1 + voice(full) + ask + completeness
 // T3: T2 + repo-mode + search
 // T4: (same as T3 — TEST_FAILURE_TRIAGE is a separate {{}} placeholder, not preamble)
@@ -582,8 +581,7 @@ export function generatePreamble(ctx: TemplateContext): string {
     generateVoiceDirective(tier),
     ...(tier >= 2 ? [generateAskUserFormat(ctx), generateCompletenessSection()] : []),
     ...(tier >= 3 ? [generateRepoModeSection(), generateSearchBeforeBuildingSection(ctx)] : []),
-    generateContributorMode(),
-    generateCompletionStatus(),
+    generateCompletionStatus(ctx),
   ];
   return sections.join('\n\n');
 }
diff --git a/setup-browser-cookies/SKILL.md b/setup-browser-cookies/SKILL.md
index 67657a6ba..e5f6e51a7 100644
--- a/setup-browser-cookies/SKILL.md
+++ b/setup-browser-cookies/SKILL.md
@@ -24,7 +24,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -45,8 +44,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"setup-browser-cookies","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"setup-browser-cookies","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -64,6 +63,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -207,24 +209,6 @@ This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLIN
 
 The user always has context you don't. Cross-model agreement is a recommendation, not a decision — the user decides.
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -250,6 +234,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -268,22 +270,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/setup-deploy/SKILL.md b/setup-deploy/SKILL.md
index 9abfb9754..26a4cb3a7 100644
--- a/setup-deploy/SKILL.md
+++ b/setup-deploy/SKILL.md
@@ -30,7 +30,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -51,8 +50,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"setup-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"setup-deploy","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -70,6 +69,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -278,24 +280,6 @@ AI makes completeness near-free. Always recommend the complete option over short
 
 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -321,6 +305,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -339,22 +341,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
diff --git a/ship/SKILL.md b/ship/SKILL.md
index 4519b6e2d..ba9b9bba4 100644
--- a/ship/SKILL.md
+++ b/ship/SKILL.md
@@ -31,7 +31,6 @@ mkdir -p ~/.gstack/sessions
 touch ~/.gstack/sessions/"$PPID"
 _SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
 find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
-_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
 _PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
 _PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
 _BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
@@ -52,8 +51,8 @@ _SESSION_ID="$$-$(date +%s)"
 echo "TELEMETRY: ${_TEL:-off}"
 echo "TEL_PROMPTED: $_TEL_PROMPTED"
 mkdir -p ~/.gstack/analytics
-if [ "${_TEL:-off}" != "off" ]; then
-  echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"ship","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
 fi
 # zsh-compatible: use find instead of glob to avoid NOMATCH error
 for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
@@ -71,6 +70,9 @@ _LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.j
 if [ -f "$_LEARN_FILE" ]; then
   _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
   echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
 else
   echo "LEARNINGS: 0"
 fi
@@ -297,24 +299,6 @@ Before building anything unfamiliar, **search first.** See `~/.claude/skills/gst
 jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
 ```
 
-## Contributor Mode
-
-If `_CONTRIB` is `true`: you are in **contributor mode**. At the end of each major workflow step, rate your gstack experience 0-10. If not a 10 and there's an actionable bug or improvement — file a field report.
-
-**File only:** gstack tooling bugs where the input was reasonable but gstack failed. **Skip:** user app bugs, network errors, auth failures on user's site.
-
-**To file:** write `~/.gstack/contributor-logs/{slug}.md`:
-```
-# {Title}
-**What I tried:** {action} | **What happened:** {result} | **Rating:** {0-10}
-## Repro
-1. {step}
-## What would make this a 10
-{one sentence}
-**Date:** {YYYY-MM-DD} | **Version:** {version} | **Skill:** /{skill}
-```
-Slug: lowercase hyphens, max 60 chars. Skip if exists. Max 3/session. File inline, don't stop.
-
 ## Completion Status Protocol
 
 When completing a skill workflow, report status using one of:
@@ -340,6 +324,24 @@ ATTEMPTED: [what you tried]
 RECOMMENDATION: [what the user should do next]
 ```
 
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+- Did you take a wrong approach and have to backtrack?
+- Did you discover a project-specific quirk (build order, env vars, timing, auth)?
+- Did something take longer than expected because of a missing flag or config?
+
+If yes, log an operational learning for future sessions:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Replace SKILL_NAME with the current skill name. Only log genuine operational discoveries.
+Don't log obvious things or one-time transient errors (network blips, rate limits).
+A good test: would knowing this save 5+ minutes in a future session? If yes, log it.
+
 ## Telemetry (run last)
 
 After the skill workflow completes (success, error, or abort), log the telemetry event.
@@ -358,22 +360,22 @@ Run this bash:
 _TEL_END=$(date +%s)
 _TEL_DUR=$(( _TEL_END - _TEL_START ))
 rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
-# Local + remote telemetry (both gated by _TEL setting)
+# Local analytics (gated on telemetry setting)
 if [ "$_TEL" != "off" ]; then
-  echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
-  if [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
-    ~/.claude/skills/gstack/bin/gstack-telemetry-log \
-      --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
-      --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
-  fi
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
 fi
 ```
 
 Replace `SKILL_NAME` with the actual skill name from frontmatter, `OUTCOME` with
 success/error/abort, and `USED_BROWSE` with true/false based on whether `$B` was used.
-If you cannot determine the outcome, use "unknown". Both local JSONL and remote
-telemetry only run if telemetry is not off. The remote binary additionally requires
-the binary to exist.
+If you cannot determine the outcome, use "unknown". The local JSONL always logs. The
+remote binary only runs if telemetry is not off and the binary exists.
 
 ## Plan Status Footer
 
@@ -1739,7 +1741,8 @@ this session, log it for future sessions:
 ```
 
 **Types:** `pattern` (reusable approach), `pitfall` (what NOT to do), `preference`
-(user stated), `architecture` (structural decision), `tool` (library/framework insight).
+(user stated), `architecture` (structural decision), `tool` (library/framework insight),
+`operational` (project environment/CLI/workflow knowledge).
 
 **Sources:** `observed` (you found this in the code), `user-stated` (user told you),
 `inferred` (AI deduction), `cross-model` (both Claude and Codex agree).
diff --git a/test/gen-skill-docs.test.ts b/test/gen-skill-docs.test.ts
index d7272a01d..186f0883a 100644
--- a/test/gen-skill-docs.test.ts
+++ b/test/gen-skill-docs.test.ts
@@ -213,11 +213,20 @@ describe('gen-skill-docs', () => {
     expect(browseTmpl).toContain('{{PREAMBLE}}');
   });
 
-  test('generated SKILL.md contains contributor mode check', () => {
+  test('generated SKILL.md contains operational self-improvement (replaced contributor mode)', () => {
     const content = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
-    expect(content).toContain('Contributor Mode');
-    expect(content).toContain('gstack_contributor');
-    expect(content).toContain('contributor-logs');
+    expect(content).not.toContain('Contributor Mode');
+    expect(content).not.toContain('gstack_contributor');
+    expect(content).not.toContain('contributor-logs');
+    expect(content).toContain('Operational Self-Improvement');
+    expect(content).toContain('gstack-learnings-log');
+    expect(content).toContain('gstack-learnings-search --limit 3');
+  });
+
+  test('generated SKILL.md with LEARNINGS_LOG contains operational type', () => {
+    // Check a skill that has LEARNINGS_LOG (e.g., review)
+    const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('operational');
   });
 
   test('generated SKILL.md contains session awareness', () => {
diff --git a/test/helpers/touchfiles.ts b/test/helpers/touchfiles.ts
index b475daad7..d21ef3476 100644
--- a/test/helpers/touchfiles.ts
+++ b/test/helpers/touchfiles.ts
@@ -41,8 +41,8 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'skillmd-no-local-binary':  ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
   'skillmd-outside-git':      ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
 
-  'contributor-mode':           ['SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
   'session-awareness':        ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'operational-learning':     ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log'],
 
   // QA (+ test-server dependency)
   'qa-quick':       ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'],
@@ -182,8 +182,8 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
   'skillmd-setup-discovery': 'gate',
   'skillmd-no-local-binary': 'gate',
   'skillmd-outside-git': 'gate',
-  'contributor-mode': 'gate',
   'session-awareness': 'gate',
+  'operational-learning': 'gate',
 
   // QA — gate for functional, periodic for quality/benchmarks
   'qa-quick': 'gate',
diff --git a/test/skill-e2e-bws.test.ts b/test/skill-e2e-bws.test.ts
index 6a611fe7c..c1a1be15d 100644
--- a/test/skill-e2e-bws.test.ts
+++ b/test/skill-e2e-bws.test.ts
@@ -20,6 +20,7 @@ let tmpDir: string;
 describeIfSelected('Skill E2E tests', [
   'browse-basic', 'browse-snapshot', 'skillmd-setup-discovery',
   'skillmd-no-local-binary', 'skillmd-outside-git', 'session-awareness',
+  'operational-learning',
 ], () => {
   beforeAll(() => {
     testServer = startTestServer();
@@ -177,49 +178,96 @@ Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
     try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
   }, 60_000);
 
-  testConcurrentIfSelected('contributor-mode', async () => {
-    const contribDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-contrib-'));
-    const logsDir = path.join(contribDir, 'contributor-logs');
-    fs.mkdirSync(logsDir, { recursive: true });
+  testConcurrentIfSelected('operational-learning', async () => {
+    const opDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-oplearn-'));
+    const gstackHome = path.join(opDir, '.gstack-home');
+
+    // Init git repo
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: opDir, stdio: 'pipe', timeout: 5000 });
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+    fs.writeFileSync(path.join(opDir, 'app.ts'), 'console.log("hello");\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial']);
+
+    // Copy bin scripts
+    const binDir = path.join(opDir, 'bin');
+    fs.mkdirSync(binDir, { recursive: true });
+    for (const script of ['gstack-learnings-log', 'gstack-slug']) {
+      fs.copyFileSync(path.join(ROOT, 'bin', script), path.join(binDir, script));
+      fs.chmodSync(path.join(binDir, script), 0o755);
+    }
+
+    // gstack-learnings-log will create the project dir automatically via gstack-slug
 
     const result = await runSkillTest({
-      prompt: `You are in contributor mode (gstack_contributor=true). You just ran this browse command and it failed:
+      prompt: `You just ran \`npm test\` in this project and it failed with this error:
 
-$ /nonexistent/browse goto https://example.com
-/nonexistent/browse: No such file or directory
+Error: --experimental-vm-modules flag is required for ESM support in this project.
+Run: npm test --experimental-vm-modules
 
-Per the contributor mode instructions, file a field report to ${logsDir}/browse-missing-binary.md using the Write tool. Include all required sections: title, what you tried, what happened, rating, repro steps, raw output, what would make it a 10, and the date/version footer.`,
-      workingDirectory: contribDir,
+Per the Operational Self-Improvement instructions below, log an operational learning about this failure.
+
+## Operational Self-Improvement
+
+Before completing, reflect on this session:
+- Did any commands fail unexpectedly?
+
+If yes, log an operational learning for future sessions:
+
+\`\`\`bash
+GSTACK_HOME="${gstackHome}" ${binDir}/gstack-learnings-log '{"skill":"qa","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+\`\`\`
+
+Replace SHORT_KEY with a kebab-case key like "esm-vm-modules-flag".
+Replace DESCRIPTION with a one-sentence description of what you learned.
+Replace N with a confidence score 1-10.
+
+Log the operational learning now. Then say what you logged.`,
+      workingDirectory: opDir,
       maxTurns: 5,
       timeout: 30_000,
-      testName: 'contributor-mode',
+      testName: 'operational-learning',
       runId,
     });
 
-    logCost('contributor mode', result);
-    // Override passed: this test intentionally triggers a browse error (nonexistent binary)
-    // so browseErrors will be non-empty — that's expected, not a failure
-    recordE2E(evalCollector, 'contributor mode report', 'Skill E2E tests', result, {
-      passed: result.exitReason === 'success',
+    logCost('operational learning', result);
+
+    const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
+
+    // Check if learnings file was created with an operational entry
+    // The slug is derived from the git repo (dirname), so search all project dirs
+    let hasOperational = false;
+    const projectsDir = path.join(gstackHome, 'projects');
+    if (fs.existsSync(projectsDir)) {
+      for (const slug of fs.readdirSync(projectsDir)) {
+        const lPath = path.join(projectsDir, slug, 'learnings.jsonl');
+        if (fs.existsSync(lPath)) {
+          const jsonl = fs.readFileSync(lPath, 'utf-8').trim();
+          if (jsonl) {
+            const entries = jsonl.split('\n').map(l => { try { return JSON.parse(l); } catch { return null; } }).filter(Boolean);
+            const opEntry = entries.find(e => e.type === 'operational');
+            if (opEntry) {
+              hasOperational = true;
+              console.log(`Operational learning logged: key="${opEntry.key}" insight="${opEntry.insight}" (slug: ${slug})`);
+              break;
+            }
+          }
+        }
+      }
+    }
+
+    recordE2E(evalCollector, 'operational learning', 'Skill E2E tests', result, {
+      passed: exitOk && hasOperational,
     });
 
-    // Verify a contributor log was created with expected format
-    const logFiles = fs.readdirSync(logsDir).filter(f => f.endsWith('.md'));
-    expect(logFiles.length).toBeGreaterThan(0);
-
-    // Verify report has key structural sections (agent may phrase differently)
-    const logContent = fs.readFileSync(path.join(logsDir, logFiles[0]), 'utf-8');
-    // Must have a title (# heading)
-    expect(logContent).toMatch(/^#\s/m);
-    // Must mention the failed command or browse
-    expect(logContent).toMatch(/browse|nonexistent|not found|no such file/i);
-    // Must have some kind of rating
-    expect(logContent).toMatch(/rating|\/10/i);
-    // Must have steps or reproduction info
-    expect(logContent).toMatch(/step|repro|reproduce/i);
+    expect(exitOk).toBe(true);
+    expect(hasOperational).toBe(true);
 
     // Clean up
-    try { fs.rmSync(contribDir, { recursive: true, force: true }); } catch {}
+    try { fs.rmSync(opDir, { recursive: true, force: true }); } catch {}
   }, 90_000);
 
   testConcurrentIfSelected('session-awareness', async () => {
diff --git a/test/skill-e2e-learnings.test.ts b/test/skill-e2e-learnings.test.ts
index dfd185135..8b6dec944 100644
--- a/test/skill-e2e-learnings.test.ts
+++ b/test/skill-e2e-learnings.test.ts
@@ -44,8 +44,9 @@ describeIfSelected('Learnings E2E', ['learnings-show'], () => {
       fs.chmodSync(path.join(binDir, script), 0o755);
     }
 
-    // Seed learnings JSONL with 3 entries of different types
-    const slug = 'test-project';
+    // Seed learnings JSONL — slug must match what gstack-slug computes.
+    // With no git remote, gstack-slug falls back to basename(workDir).
+    const slug = path.basename(workDir).replace(/[^a-zA-Z0-9._-]/g, '');
     const projectDir = path.join(gstackHome, 'projects', slug);
     fs.mkdirSync(projectDir, { recursive: true });
 
@@ -67,6 +68,11 @@ describeIfSelected('Learnings E2E', ['learnings-show'], () => {
         insight: 'User wants rubocop to run before every commit, no exceptions.',
         confidence: 10, source: 'user-stated', ts: new Date().toISOString(),
       },
+      {
+        skill: 'qa', type: 'operational', key: 'test-timeout-flag',
+        insight: 'bun test requires --timeout 30000 for E2E tests in this project.',
+        confidence: 9, source: 'observed', ts: new Date().toISOString(),
+      },
     ];
 
     fs.writeFileSync(
diff --git a/test/skill-e2e.test.ts b/test/skill-e2e.test.ts
index 91c95f7a7..f1a13cec9 100644
--- a/test/skill-e2e.test.ts
+++ b/test/skill-e2e.test.ts
@@ -325,62 +325,6 @@ Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
     try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
   }, 60_000);
 
-  testIfSelected('contributor-mode', async () => {
-    const contribDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-contrib-'));
-    const logsDir = path.join(contribDir, 'contributor-logs');
-    fs.mkdirSync(logsDir, { recursive: true });
-
-    // Extract contributor mode instructions from generated SKILL.md
-    const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
-    const contribStart = skillMd.indexOf('## Contributor Mode');
-    const contribEnd = skillMd.indexOf('\n## ', contribStart + 1);
-    const contribBlock = skillMd.slice(contribStart, contribEnd > 0 ? contribEnd : undefined);
-
-    const result = await runSkillTest({
-      prompt: `You are in contributor mode (_CONTRIB=true).
-
-${contribBlock}
-
-OVERRIDE: Write contributor logs to ${logsDir}/ instead of ~/.gstack/contributor-logs/
-
-Now try this browse command (it will fail — there is no binary at this path):
-/nonexistent/path/browse goto https://example.com
-
-This is a gstack issue (the browse binary is missing/misconfigured).
-File a contributor report about this issue. Then tell me what you filed.`,
-      workingDirectory: contribDir,
-      maxTurns: 8,
-      timeout: 60_000,
-      testName: 'contributor-mode',
-      runId,
-    });
-
-    logCost('contributor mode', result);
-    // Override passed: this test intentionally triggers a browse error (nonexistent binary)
-    // so browseErrors will be non-empty — that's expected, not a failure
-    recordE2E('contributor mode report', 'Skill E2E tests', result, {
-      passed: result.exitReason === 'success',
-    });
-
-    // Verify a contributor log was created with expected format
-    const logFiles = fs.readdirSync(logsDir).filter(f => f.endsWith('.md'));
-    expect(logFiles.length).toBeGreaterThan(0);
-
-    // Verify new reflection-based format
-    const logContent = fs.readFileSync(path.join(logsDir, logFiles[0]), 'utf-8');
-    expect(logContent).toContain('Hey gstack team');
-    expect(logContent).toContain('What I was trying to do');
-    expect(logContent).toContain('What happened instead');
-    expect(logContent).toMatch(/rating/i);
-    // Verify report has repro steps (agent may use "Steps to reproduce", "Repro Steps", etc.)
-    expect(logContent).toMatch(/repro|steps to reproduce|how to reproduce/i);
-    // Verify report has date/version footer (agent may format differently)
-    expect(logContent).toMatch(/date.*2026|2026.*date/i);
-
-    // Clean up
-    try { fs.rmSync(contribDir, { recursive: true, force: true }); } catch {}
-  }, 90_000);
-
   testIfSelected('session-awareness', async () => {
     const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));
 
diff --git a/test/skill-validation.test.ts b/test/skill-validation.test.ts
index 50beaa907..20c6971e1 100644
--- a/test/skill-validation.test.ts
+++ b/test/skill-validation.test.ts
@@ -735,45 +735,8 @@ describe('investigate skill structure', () => {
   }
 });
 
-// --- Contributor mode preamble structure validation ---
-
-describe('Contributor mode preamble structure', () => {
-  const skillsWithPreamble = [
-    'SKILL.md', 'browse/SKILL.md', 'qa/SKILL.md',
-    'qa-only/SKILL.md',
-    'setup-browser-cookies/SKILL.md',
-    'ship/SKILL.md', 'review/SKILL.md',
-    'plan-ceo-review/SKILL.md', 'plan-eng-review/SKILL.md',
-    'retro/SKILL.md',
-    'plan-design-review/SKILL.md',
-    'design-review/SKILL.md',
-    'design-consultation/SKILL.md',
-    'document-release/SKILL.md',
-    'canary/SKILL.md',
-    'benchmark/SKILL.md',
-    'land-and-deploy/SKILL.md',
-    'setup-deploy/SKILL.md',
-  ];
-
-  for (const skill of skillsWithPreamble) {
-    test(`${skill} has 0-10 rating in contributor mode`, () => {
-      const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
-      expect(content).toContain('0-10');
-      expect(content).toContain('Rating');
-    });
-
-    test(`${skill} has "what would make this a 10" field`, () => {
-      const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
-      expect(content).toContain('What would make this a 10');
-    });
-
-    test(`${skill} uses periodic reflection (not per-command)`, () => {
-      const content = fs.readFileSync(path.join(ROOT, skill), 'utf-8');
-      expect(content).toContain('workflow step');
-      expect(content).not.toContain('After you use gstack-provided CLIs');
-    });
-  }
-});
+// Contributor mode was removed in v0.13.10.0 — replaced by operational self-improvement.
+// Tests for contributor mode preamble structure are no longer applicable.
 
 describe('Enum & Value Completeness in review checklist', () => {
   const checklist = fs.readFileSync(path.join(ROOT, 'review', 'checklist.md'), 'utf-8');
diff --git a/test/touchfiles.test.ts b/test/touchfiles.test.ts
index 2bce835b5..d4aee2027 100644
--- a/test/touchfiles.test.ts
+++ b/test/touchfiles.test.ts
@@ -101,7 +101,7 @@ describe('selectTests', () => {
     expect(result.reason).toBe('diff');
     // Should include tests that depend on gen-skill-docs.ts
     expect(result.selected).toContain('skillmd-setup-discovery');
-    expect(result.selected).toContain('contributor-mode');
+    expect(result.selected).toContain('session-awareness');
     expect(result.selected).toContain('journey-ideation');
     // Should NOT include tests that don't depend on it
     expect(result.selected).not.toContain('retro');
@@ -144,7 +144,7 @@ describe('selectTests', () => {
     const result = selectTests(['SKILL.md.tmpl'], E2E_TOUCHFILES);
     // Should select the 7 tests that depend on root SKILL.md
     expect(result.selected).toContain('skillmd-setup-discovery');
-    expect(result.selected).toContain('contributor-mode');
+    expect(result.selected).toContain('session-awareness');
     expect(result.selected).toContain('session-awareness');
     // Also selects journey routing tests (SKILL.md.tmpl in their touchfiles)
     expect(result.selected).toContain('journey-ideation');