davidbzyk · Oct 11, 2026 · Oct 11, 2026 · Oct 11, 2026
diff --git a/README.md b/README.md
@@ -33,7 +33,7 @@ turn the review into a self-improving workflow. This README is its summary.
 |---|---|---|
 | The review team | Seven reviewers (security, tests, correctness, architecture, code quality, compliance, language) and a validator, run by one orchestrator, merged into one de-duplicated set of findings | `src/review_core/`, `src/plugin/` |
 | The CI action | Reviews every pull request on a GitHub runner with Codex and posts the findings like the commercial review bots do | `action/` |
-| The evals | Rubric-graded Harbor tasks built from real, confirmed bugs, for any agent, harness, model and judge | `evals/` |
+| The evals | Rubric-graded Harbor tasks built from real, confirmed bugs, run by one agent or by the whole review team, for any agent, harness, model and judge | `evals/` |
 | The research | The voiceover cases, the frozen answer keys, the OKF notes and every scored review | `research/` |
 
 ## The research: does giving review agents more context help?
@@ -145,6 +145,11 @@ scores how many of them a review finds. The agent, harness, model and judge are
 run time, so the same tasks compare any of them.
 
 - `evals/tasks/vo-t01` to `vo-t06`: the six scored voiceover changes, one task per pull request.
+- `evals/team-tasks/vo-t01` to `vo-t06`: the same six changes reviewed by the team as it ships. Each
+  is a multi-step Harbor task: seven reviewer steps, each a fresh agent session given the
+  orchestrator's own message, then the validator step, whose final findings the same judge grades.
+  One trajectory per step, so you can see each reviewer come in and out. The single-agent tasks
+  above are the baseline.
 - `evals/cases/cr-self-01`: this repository's own history, the first commit of the CI action and
   the 18 confirmed bugs it contained. Can the review tool find the bugs in itself?
 

diff --git a/ci/tracked-paths.toml b/ci/tracked-paths.toml
@@ -11,10 +11,11 @@ deny_globs = [
   ".env.*",
   # The general-environments eval tasks hold private code and accepted comments: never public.
   "evals/tasks/ge-*",
+  "evals/team-tasks/ge-*",
 ]
 # Paths whose case material is published on purpose: the voiceover eval tasks (public repository,
 # key unsealed after the scored run, decision 92). Deny globs still win.
-allow_globs = ["evals/tasks/vo-*"]
+allow_globs = ["evals/tasks/vo-*", "evals/team-tasks/vo-*"]
 # The denied names those paths may still hold: each task's change archive.
 published_names = ["repo.tar.gz"]
 # Templates of .env that hold no values.

diff --git a/evals/tasks/vo-t01/environment/Dockerfile b/evals/tasks/vo-t01/environment/Dockerfile
diff --git a/evals/tasks/vo-t01/environment/repo.tar.gz b/evals/tasks/vo-t01/environment/repo.tar.gz
diff --git a/evals/tasks/vo-t01/tests/judge_prelude.sh b/evals/tasks/vo-t01/tests/judge_prelude.sh
diff --git a/evals/tasks/vo-t02/environment/Dockerfile b/evals/tasks/vo-t02/environment/Dockerfile
diff --git a/evals/tasks/vo-t02/environment/repo.tar.gz b/evals/tasks/vo-t02/environment/repo.tar.gz
diff --git a/evals/tasks/vo-t02/tests/judge_prelude.sh b/evals/tasks/vo-t02/tests/judge_prelude.sh
diff --git a/evals/tasks/vo-t03/environment/Dockerfile b/evals/tasks/vo-t03/environment/Dockerfile
diff --git a/evals/tasks/vo-t03/environment/repo.tar.gz b/evals/tasks/vo-t03/environment/repo.tar.gz
diff --git a/evals/tasks/vo-t04/environment/Dockerfile b/evals/tasks/vo-t04/environment/Dockerfile
diff --git a/evals/tasks/vo-t04/environment/repo.tar.gz b/evals/tasks/vo-t04/environment/repo.tar.gz
diff --git a/evals/tasks/vo-t05/environment/Dockerfile b/evals/tasks/vo-t05/environment/Dockerfile
diff --git a/evals/tasks/vo-t05/environment/repo.tar.gz b/evals/tasks/vo-t05/environment/repo.tar.gz
diff --git a/evals/tasks/vo-t06/environment/Dockerfile b/evals/tasks/vo-t06/environment/Dockerfile
diff --git a/evals/tasks/vo-t06/environment/repo.tar.gz b/evals/tasks/vo-t06/environment/repo.tar.gz
diff --git a/evals/team-tasks/vo-t01/README.md b/evals/team-tasks/vo-t01/README.md
diff --git a/evals/team-tasks/vo-t01/environment/Dockerfile b/evals/team-tasks/vo-t01/environment/Dockerfile
diff --git a/evals/team-tasks/vo-t01/environment/collect_findings.py b/evals/team-tasks/vo-t01/environment/collect_findings.py
diff --git a/evals/team-tasks/vo-t01/environment/repo.tar.gz b/evals/team-tasks/vo-t01/environment/repo.tar.gz