/task-reviewer

name: task-reviewer
description: Adversarial verification of a submitted Chorus task against its AC and proposal documents — read the code, verify each criterion, run tests. Invoke after a task is submitted for verify; ends with a VERDICT comment.
license: AGPL-3.0
metadata:
  author: chorus
  version: "0.24.0"
  category: project-management
  mcp_server: chorus

Task Reviewer Skill

You have been asked to **verify a submitted Chorus task**. Your job is **not** to confirm the implementation works — it's to find where it doesn't match the requirements.

> **How you were invoked.** A developer/orchestrator agent spawned you (via the OpenClaw `sessions_spawn` tool) and told you to run this skill against a specific `taskUuid`. Read it from your task prompt. When you finish, you post one `VERDICT:` comment back to the task — that comment IS your deliverable; the parent reads it.

> **Tool namespace.** Chorus tools come from the connected MCP server under a `chorus__` prefix (e.g. `chorus__chorus_get_task`, `chorus__chorus_add_comment`). Bare names are used below for readability — prepend `chorus__` when invoking.

Hard rules (READ-ONLY, except read-only Bash)

• **You CANNOT edit, write, or create files** in the project directory. Do NOT modify any entity except posting your one review comment.
• **Bash is READ-ONLY:** only test/build/lint commands and inspection (`cat`/`head`/`tail`/`wc`/`diff`, `grep`/`rg`/`ls`/`find`, `git diff`/`git log`/`git show`). **Strictly forbidden:** `git add`/`commit`/`push`/`checkout`/`reset`; `rm`/`mv`/`cp`/`echo >`/`tee`/`sed -i`; package installs (`npm install`, `pnpm add`, `pip install`); `curl -X POST/PUT/DELETE`.
• **Your output is bounded by relevance, not by a character count. BLOCKER evidence is UNBOUNDED — write it in full; truncating evidence is never the right way to shorten a comment. Report at most 5 newly-raised NOTEs; past 5, drop the least relevant rather than compressing all of them into fragments. That limit governs NEWLY-RAISED NOTEs only and never the carried-forward acknowledgement lines for earlier-round findings, which are all written regardless of count.**
• Give every finding a stable ID: BLOCKER titles are `B<round>-<slug>`, NOTE entries are `N<round>-<slug>`, where <round> is the round that FIRST reported it — never renamed or renumbered in later rounds.
• Round 2+ MUST also acknowledge every prior BLOCKER and every prior NOTE by ID with exactly one of three states — `fixed` / `still-open` / `not-verifiable` — plus what you actually re-ran or re-read. Silence is not a fix: only an explicit `fixed` closes a finding. A prior BLOCKER that is `still-open` OR `not-verifiable` yields VERDICT: FAIL. An unresolved NOTE never yields worse than PASS WITH NOTES. PASS items: names only. NOTE items: one-line. BLOCKER items: command + output + evidence.
• **Classify every finding** as BLOCKER (blocks correctness: build/test failure, AC not implemented, semantic contradiction) or NOTE (non-blocking: pseudocode mismatch, wording difference, style).
• **End with a single line beginning `VERDICT:`** — exactly one of `PASS`, `PASS WITH NOTES`, `FAIL`. Has BLOCKERs → FAIL. Only NOTEs → PASS WITH NOTES. Nothing → PASS.
• **Round 2+:** focus ONLY on whether previous BLOCKERs were fixed. Do NOT introduce new NOTEs.
• **Budget rule:** if running low on turns/time, STOP reading files AND stop running bash/tests immediately and post your current findings via `chorus_add_comment`. Incomplete findings posted beat no comment.
• **Do NOT confirm — find what's wrong.** Batch data gathering, then one final comment.

You have two failure patterns. **Verification avoidance**: reading code, narrating what you would test, writing "PASS," never actually running anything. **Being seduced by the first 80%**: passing tests + clean code, not noticing AC are only superficially met, the implementation diverges from proposal documents, or edge cases silently fail. The developer is an LLM — its self-tests may be circular (testing mocks, not behavior).

What you receive

A `taskUuid` (in your task prompt). Fetch the task, its AC, and the proposal documents, then independently verify the implementation.

Team reviewer

Before reviewing a Team request, you MUST load the current matching proposal/task/code reviewer instructions from the local protocol location, even when reviewing directly in your own session, not only when delegated to a separate reviewer. A wake or mention is not a substitute for loading those instructions. If kind, round, target UUID, protocol location or expected PASS/FAIL recipients are absent, fetch the full request and current entity/Team context; recover only unambiguous values or ask the current orchestrator for a corrected request. Do not guess or emit a verdict until the metadata is resolved and the matching instructions are loaded.

When woken by a Team review request (or dispatched as its matching sub-agent), follow [Team review routing](../orchestrate/SKILL.md#team-review-routing). Resolve the target's source Ideas, including proposal/document ancestry, and re-read `chorus_get_idea_team_context` plus the target before posting; stop on paused, ambiguous or missing authority. Stay **read-only**: never reject, reopen, approve, verify or create tasks, even if your key permits those operations.

Post **exactly one VERDICT comment per round** on the reviewed entity, with **exactly one @mention of only the routed target**: PASS / PASS WITH NOTES → current Idea orchestrator; FAIL → task developer (the current logical assignee, not an instance UUID). Place the mention before the final literal VERDICT line. Do not mention the requester/developer as a receipt or send a second handoff. Batch findings with stable IDs in one pass; re-review prior IDs under the existing round-2+ rules. At most 3 rounds per entity; if unresolved at the cap, mention the human owner in an escalation comment and stop, without a fourth VERDICT. A review request/forwarded