agent-review
Skill2 starsChanged 26 days agoMITView on GitHub
Use when hooks, settings, agent files, skills or MCP configuration must be reviewed in a fresh context against the Claude Code and MCP docs for security and compliance. Runs the mcp-agent-engineer in a fresh context and writes a ranked findings file to work\reports\reviews\<date>-<slug>.md.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- facebookresearch/autoform-bottheir own version, first seen Nov 12, 2026
- blamechris/chroxytheir own version, first seen Nov 8, 2026
- khoralabs/skillstheir own version, first seen Nov 1, 2026
- IlyaSemenov/agent-review-skilltheir own version, first seen Oct 31, 2026
- alexaiarchitect/google-adk-skillstheir own version, first seen Oct 20, 2026
- fabioc-aloha/Alex_ACT_Editiontheir own version, first seen Oct 13, 2026
Used with
Projects with it also use commit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 3 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- DmNote-App/DmNote★ 4.3ksame name
- foldkit/foldkit★ 1.1ksame name
- Tsuzat/Edra★ 675same name
- facebookresearch/autoform-bot★ 143same name
- blamechris/chroxy★ 8same name
- IlyaSemenov/agent-review-skill★ 4same name
- ethanaubuchon/dossier-tradecraft★ 3same name
- khoralabs/skills★ 1same name
- ngc-shj/claude-code-config★ 1same name
- alexaiarchitect/google-adk-skills★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-mesh-cleanSkill
- cad-buildSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- ortho-sheetSkill
- pi-power-budgetSkill
- preprint-checkSkill
- promo-planSkill
- qa-gateSkill
- render-criticSkill
- research-oneSkill
- research-topicSkill
- retopoSkill
- safety-sheetSkill
- sculptSkill
- slicer-questionSkill
- style-bibleSkill
- tech-packSkill
- unit-costSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
After any change to .claude\settings.json, tools\hooks\, .claude\agents\, .claude\skills\ or .mcp.json, or before a new MCP server is …
- Very specific: line 16
Read the files. Run the shipped checks with .venv\Scripts\python.exe: the tests under tools\tests\ that cover the reviewed files (for …
- Distinctive: line 17
Write the review: closed / open / new findings, severity, fix, evidence.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
Input: $ARGUMENTS, as <slug> | <paths>. Output: work\reports\reviews\YYYY-MM-DD-<slug>.md with findings ranked by severity, each with a docs quote or a test result and a concrete fix. No installs, no settings changes.
When to use
After any change to .claude\settings.json, tools\hooks\, .claude\agents\, .claude\skills\ or .mcp.json, or before a new MCP server is proposed. Not for building a new MCP tool (use /mcp-new-tool).
Steps
- Fetch the relevant docs this run (https://docs.anthropic.com/en/docs/claude-code/hooks, https://docs.anthropic.com/en/docs/claude-code/settings, https://docs.anthropic.com/en/docs/claude-code/sub-agents, https://docs.anthropic.com/en/docs/claude-code/skills, https://docs.anthropic.com/en/docs/claude-code/mcp, https://modelcontextprotocol.io/specification/latest; curl fallback on HTTP 402/403) and quote the lines you rely on.
- Read the files. Run the shipped checks with
.venv\Scripts\python.exe: the tests undertools\tests\that cover the reviewed files (for example the guard-hook tests) andtools\check_skill.pyon any skill. Add targeted probes (crafted hook inputs on stdin) without modifying anything. - Write the review: closed / open / new findings, severity, fix, evidence. Secrets never appear in the file.
- Return the path and the open-finding count.
Common rationalizations
| Rationalization | Reality |
| "The hook fired once, it works." | A guard hook that passed its first run can still be bypassed by another tool name, path form or quoting. Probe the edge cases. |
| "I'll just fix it while I'm here." | Reviewer and fixer are different contexts. Report; the lead fixes. |
Red flags
- A finding without a docs quote or a test result.
- Any edit to settings or hooks during the review.
Verification
- Review file written; findings ranked with fixes.
- Tests run and results quoted.
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.

