swcstudiospace/agent-swarm/a09-reviewer
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
A09 REV Code Reviewer — Review gate. Reviews diffs for correctness, standards and contract adherence and issues the signed review verdict with structured findings. Read-only on product code. Use when the user runs /a09-reviewer, asks for REV, or the swarm assigns capability review.code, review.standards, gate.review.
Install
npx vskill@latest install swcstudiospace/agent-swarm/a09-reviewerSKILL.md
Code Reviewer (A09 REV)
Subagent body: prompts/A09-reviewer.md (do not paste it here). Generated agents: .claude/agents/a09-reviewer.md and .grok/agents/a09-reviewer.md.
When to Use
- The assignment capability is one of: review.code, review.standards, gate.review.
- The user names this agent, slug
a09-reviewer, or codeREV. - Use when the user runs /a09-reviewer.
Don't use for: Do not edit product code.
Prerequisites
- Swarm root with
agents.json,scripts/,swarm/. SWARM_DIR(default<git toplevel>/.swarm, made absolute).python3and/orbunon PATH.- Signed
task.assignwith task_id and correlation_id.
How to Run
python3 scripts/rev_gate.py --task-id $TASK --correlation-id $CORR --jsonbun scripts/ts/rev_gate.ts --task-id $TASK --correlation-id $CORR --jsonpython3 scripts/rev_greptile_ingest.py --task-id $TASK --correlation-id $CORR --jsonbun scripts/ts/rev_greptile_ingest.ts --task-id $TASK --correlation-id $CORR --json
Procedure
- Validate the signed task.assign. Echo task_id and correlation_id.
- Read upstream artifacts in consumes: code.patch, api.contract, acceptance.criteria, schema.migration.
- Run the scripts above. Never fabricate JSON.
- Write only review.verdict, gate.verdict, review.comments.
- Finish with markdown summary + one fenced json
task.result.
Pitfalls
- Missing optional binary →
skipped:tool-missing, do not invent results. - L3/L4 → BLOCKED needs=human-approval.
- Third gate failure → do not retry; A01 escalates.
Verification
- Script JSON
statusis ok or fail with findings. - Final json block matches the prompt
<output_format>. - No writes outside this agent's single-writer zone.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/a09-reviewer/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/swcstudiospace/agent-swarm/a09-reviewer)