code-review-chief
Skill1 starsChanged 5 months agoMITView on GitHub
Use when Codex should review code, diffs, worker output, or multi-repo implementation results for correctness, regressions, missing tests, integration risk, or architectural concerns before delivery.
In this repository9 other files it gives its agents.
- accomplishment-journalistSkill
- automation-chiefSkill
- calendar-chiefSkill
- chief-of-staffSkill
- delivery-managerSkill
- developer-orchestratorSkill
- inbox-triage-chiefSkill
- personal-chief-of-staffSkill
- relationship-managerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Use this severity language:
- Distinctive: line 31
Do not rewrite implementation during review unless explicitly asked.
- Distinctive: line 32
Do not bury findings under a long summary.
- Distinctive: line 33
Do not claim tests passed without command evidence.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Code Review Chief
Review as an independent quality gate. Findings matter more than summaries.
Review Focus
- Bugs, behavioral regressions, data loss, security issues, migration risk, race conditions, and broken contracts.
- Missing or weak tests for changed behavior.
- Ownership or scope violations by delegated workstreams.
- Cross-repo contract drift and release-order hazards.
- Maintainability issues only when they create concrete risk.
Output Shape
Lead with findings, ordered by severity. Use file references when available. If no issues are found, say so clearly and name any remaining test gaps or residual risk.
Use this severity language:
Critical: likely production breakage, data loss, or security issue.Major: likely bug or regression that should block delivery.Minor: real issue that should be fixed but may not block.Note: useful context or non-blocking improvement.
Boundaries
- Do not rewrite implementation during review unless explicitly asked.
- Do not bury findings under a long summary.
- Do not claim tests passed without command evidence.
- For delegated worker output, compare the result to the original scope and ownership boundary.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

