feat(aidd-dev): rename todo to batch and report each agent's outcome

aidd_docs/README.md

@@ -104,7 +104,7 @@ AIDD is delivered as a plugin marketplace. Pick what you need; do not install ev
 | ------------ | ------------------------------------------------------------------------------------------------------------------- |
 | aidd-context | 00-onboard, 01-bootstrap, 02-project-memory, 03-context-generate, 09-mermaid, 10-learn, 11-explore                    |
 | aidd-refine  | 01-brainstorm, 02-challenge, 03-shadow-areas, 04-fact-check                                                        |
-| aidd-dev     | 01-plan, 02-implement, 03-assert, 04-audit, 05-review, 06-test, 07-refactor, 08-debug, 09-for-sure, 10-todo       |
+| aidd-dev     | 01-plan, 02-implement, 03-assert, 04-audit, 05-review, 06-test, 07-refactor, 08-debug, 09-for-sure, 10-batch       |
 | aidd-orchestrator | 00-async-dev, 01-sdlc                                                                                         |
 | aidd-vcs     | 01-commit, 02-pull-request, 03-release-tag, 04-issue-create                                                         |
 | aidd-pm      | 01-ticket-info, 02-user-stories, 03-prd, 04-spec, 05-spike, 06-product-brief, 07-epic, 08-three-amigos, 09-defect, 10-task |

docs/CATALOG.md

@@ -49,7 +49,7 @@ Code transformation: plan, implement, assert, audit, review, test, refactor, deb
 | `07-refactor`   | Improve code without changing behavior across four axes                    | `01-performance`, `02-security`, `03-cleanup`, `04-architecture`                 |
 | `08-debug`      | Reproduce and fix bugs with a test-driven workflow                         | `01-reproduce`, `02-debug`, `03-reflect-issue`                                   |
 | `09-for-sure`   | Iterative loop that retries until a success condition is met               | `01-init-tracking`, `02-auto-accept`, `03-autonomous-loop`                       |
-| `10-todo`       | Split the prompt into independent todos, run one implementer agent per todo in parallel | `01-todo`                                                            |
+| `10-batch`       | Execute independent tasks in parallel and summarize each agent's status and result | `01-batch`                                                            |
 
 ## 📋 aidd-pm
 

plugins/aidd-dev/.claude-plugin/plugin.json

@@ -17,7 +17,7 @@
     "./skills/07-refactor",
     "./skills/08-debug",
     "./skills/09-for-sure",
-    "./skills/10-todo"
+    "./skills/10-batch"
   ],
   "agents": [
     "./agents/executor.md",

plugins/aidd-dev/CATALOG.md

@@ -18,7 +18,7 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai
   - [`skills/07-refactor`](#skills07-refactor)
   - [`skills/08-debug`](#skills08-debug)
   - [`skills/09-for-sure`](#skills09-for-sure)
-  - [`skills/10-todo`](#skills10-todo)
+  - [`skills/10-batch`](#skills10-batch)
 
 ---
 
@@ -137,10 +137,10 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai
 | `references` | [autonomous-loop-log-format.md](skills/09-for-sure/references/autonomous-loop-log-format.md) | - |
 | `-` | [SKILL.md](skills/09-for-sure/SKILL.md) | `Run an iterative agent loop that retries until a runnable success condition passes. Use when the user says "for sure", "keep trying until", or wants guaranteed completion against a success command. Not for one-shot tasks or uncheckable goals.` |
 
-#### `skills/10-todo`
+#### `skills/10-batch`
 
 | Group | File | Description |
 |-------|------|---|
-| `actions` | [01-todo.md](skills/10-todo/actions/01-todo.md) | - |
-| `-` | [SKILL.md](skills/10-todo/SKILL.md) | `Split the user prompt into independent todos and run one executor agent per todo in parallel, then report a minimal table. Use when the user says "todo" or asks to fan out a multi-part request into parallel implementations.` |
+| `actions` | [01-batch.md](skills/10-batch/actions/01-batch.md) | - |
+| `-` | [SKILL.md](skills/10-batch/SKILL.md) | `Split a request into independent tasks, execute them in parallel, and summarize each agent's task, status, and result. Use when the user says "batch" or asks to execute a multi-part request in parallel.` |
 

plugins/aidd-dev/README.md

@@ -8,7 +8,7 @@ Code transformation plugin for the AI-Driven Development framework.
 
 First time? Install with `/plugin install aidd-dev@aidd-framework`, then run `aidd-dev:01-plan`.
 
-Covers code transformation: planning, implementation, assertions, audits, code review, testing, refactoring, debugging, for-sure, and parallel todo fan-out. Also hosts AI agents.
+Covers code transformation: planning, implementation, assertions, audits, code review, testing, refactoring, debugging, for-sure, and parallel batch execution. Also hosts AI agents.
 
 ## Skills
 
@@ -23,7 +23,7 @@ Covers code transformation: planning, implementation, assertions, audits, code r
 | [2.7] | [refactor](skills/07-refactor/SKILL.md) | Optimize code for performance and fix security vulnerabilities following OWASP guidelines. |
 | [2.8] | [debug](skills/08-debug/SKILL.md) | Reproduce and fix bugs systematically using test-driven workflow, root cause analysis, and hypothesis validation. |
 | [2.9] | [for-sure](skills/09-for-sure/SKILL.md) | Iterative agent loop that tracks attempts and retries until a success condition is met. |
-| [2.10] | [todo](skills/10-todo/SKILL.md) | Split the prompt into independent todos, run one executor agent per todo in parallel, then report a minimal table. |
+| [2.10] | [batch](skills/10-batch/SKILL.md) | Split a request into independent tasks, execute them in parallel, and summarize each agent's task, status, and result. |
 
 ## Agents
 

plugins/aidd-dev/skills/10-batch/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: 10-batch
+description: Split a request into independent tasks, execute them in parallel, and summarize each agent's task, status, and result. Use when the user says "batch" or asks to execute a multi-part request in parallel.
+argument-hint: requirement
+---
+
+# Batch
+
+Turn one prompt into independent tasks, implement them in parallel, report each agent's outcome.
+
+## Actions
+
+```markdown
+actions/01-batch.md
+```
+
+Before running an action, read its file in `actions/`, not only the table or assets.

plugins/aidd-dev/skills/10-batch/actions/01-batch.md

@@ -0,0 +1,36 @@
+# 01 - Batch
+
+Split the user prompt into independent tasks, implement each in parallel, report.
+
+## Input
+User's requirement.
+
+## Output
+```markdown
+| Agent | Task | Status | Result |
+| ----- | ---- | ------ | ------ |
+```
+
+One row per dispatched agent, identified by its name or ID. Status is `Done` (task completed with validation evidence), `Blocked` (an unmet prerequisite prevents completion), or `Failed` (execution failed). Result summarizes the outcome and changed files, or the reason and remaining work for a blocked or failed task.
+
+## Process
+
+1. **Read.** Take `prompt` from the arguments; if empty, ask the user.
+2. **Split.** Divide the prompt into distinct, independent tasks. Inline, no agent.
+3. **Launch.** Spawn one `executor` agent per task, all in parallel (one message, multiple Task calls). Track each agent's name or ID and assigned task. Each agent prompt mandates, in order:
+   ```markdown
+   1. Refine the task first: run a non-interactive refine capability if one is available (discovered at runtime, never a hardcoded plugin name); otherwise restate the task clearly and resolve obvious ambiguity inline. Never block on the user.
+   2. Implement the refined task.
+   3. Return a one-line summary with status, outcome, changed files, and validation evidence; if blocked or failed, include the reason and remaining work.
+   ```
+4. **Collect.** Wait for every dispatched agent to finish or report a blocker. Preserve blocked and failed outcomes; mark an agent that exits with an error as `Failed` even if it returns no summary.
+5. **Report.** Print exactly one final table using the output columns, nothing else. Base each status and result on the collected evidence.
+
+## Test
+
+- Every dispatched agent is one row in the table, including blocked or failed agents.
+- Each row identifies the agent and its assigned task, status, and result.
+- Agents were spawned in a single parallel batch.
+- Each agent ran a refine step before implementing.
+- The final table follows collection of all agents' outcomes; `Done` requires completion and validation evidence.
+- No output besides the table.

plugins/aidd-orchestrator/skills/01-sdlc/references/03-check.md

@@ -10,7 +10,7 @@
 A checker's finding is routed by what it is about. A refusal the user gives at a pause is not one of these: `mode.md` routes that by artifact.
 
 - Product or contract findings are the next Frame source.
-- Independent implementation findings go through Todo; dependent repairs stay together in Deliver.
+- Independent implementation findings go through Batch; dependent repairs stay together in Deliver.
 - Re-enter Check after every new candidate.
 - Once the review has cleared, only a finding that contradicts the contract reopens a zone: carry any other onto the request as a note.
 - A finding already acted on is never routed twice. Repaired or not, it is a decision that requires user authority, and no request opens until that arrives.
@@ -43,7 +43,7 @@ flowchart TD
     direction TB
     Findings["$findings"]
     Frame["01 Frame"]
-    Todo["/aidd-dev:10-todo"]
+    Batch["/aidd-dev:10-batch"]
     Deliver["02 Deliver"]
   end
 
@@ -63,17 +63,17 @@ flowchart TD
   Challenge -- "Return actionable challenge findings." --> Findings
   Challenge -- "When the outcome is trustworthy, open the draft pull request." --> PullRequest
   Findings -- "Use product findings as the next Frame source." --> Frame
-  Findings -- "Repair independent implementation findings in parallel." --> Todo
+  Findings -- "Repair independent implementation findings in parallel." --> Batch
   Findings -- "Repair dependent implementation findings together." --> Deliver
-  Todo --> Deliver
+  Batch --> Deliver
   PullRequest --> PullRequestUrl
 
   classDef skill fill:#DBEAFE,stroke:#2563EB,color:#1E3A8A,stroke-width:2px
   classDef agent fill:#F3E8FF,stroke:#9333EA,color:#581C87,stroke-width:2px
   classDef artifact fill:#DCFCE7,stroke:#16A34A,color:#14532D,stroke-width:2px
   classDef zone fill:#F1F5F9,stroke:#64748B,color:#0F172A,stroke-width:2px
 
-  class Review,Challenge,Todo,PullRequest skill
+  class Review,Challenge,Batch,PullRequest skill
   class Checker agent
   class Contract,Plan,CommittedCandidate,ValidationReports,Findings,PullRequestUrl artifact
   class Frame,Deliver zone

scripts/__tests__/architecture-rules.property.test.js

@@ -226,9 +226,9 @@ test("every router in the tree cites every action it provides", () => {
 });
 
 test("removing a real router's citation is caught, for every action in the tree", () => {
-  // `aidd-dev:10-todo` names its one action as a fenced path rather than a table row, so there
+  // `aidd-dev:10-batch` names its one action as a fenced path rather than a table row, so there
   // is no row to remove and nothing to catch. It is the one documented exception.
-  const FENCED_PATH_SKILL = "plugins/aidd-dev/skills/10-todo/SKILL.md";
+  const FENCED_PATH_SKILL = "plugins/aidd-dev/skills/10-batch/SKILL.md";
   const missed = [];
   let checked = 0;
 

scripts/__tests__/architecture-rules.test.js

@@ -424,7 +424,7 @@ test("a fenced example table inside the Actions section cites nothing", () => {
   assert.match(violations[0].message, /never names action file "02-second\.md"/);
 });
 
-test("a fenced actions/<name>.md path still cites, the way 10-todo does", () => {
+test("a fenced actions/<name>.md path still cites, the way 10-batch does", () => {
   const content = [
     "# Fenced path skill",
     "",

scripts/lib/architecture-rules.js

@@ -230,7 +230,7 @@ function matchesOf(pattern, text) {
 
 /**
  * The three citation shapes. Only the `actions/<name>.md` path is read through a fence, because
- * `aidd-dev:10-todo` cites its one action that way; a backticked file name inside a fence is an
+ * `aidd-dev:10-batch` cites its one action that way; a backticked file name inside a fence is an
  * example. A word loose in prose is never a citation.
  */
 function citationsIn(blankedLines, rawLines) {