agentleFS
makedirectorymakedirectory/ModelPeer/.claude/skills/cross-model-review/SKILL.md

cross-model-review

Skill1 starsChanged 3 months agoMITView on GitHub

Run an independent cross-model review of the current Git diff with Model Peer. Every installed model reviews the same changes without seeing the others' conclusions, then a synthesizer reconciles them. Use before opening a pull request, after any change to security-sensitive code, and when you want more than your own read on a change you just wrote.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. github/lever★ 279same name
    2. NoobyGains/godmode★ 120same name
    3. hyperb1iss/hyperskills★ 36same name
    4. fotowizzard/taskctl-oss★ 1same name
    5. hiteshbandhu/skills-i-use★ 1same name

    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 repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    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
  1. Distinctive:

    Every installed model receives the same Git status and patch — tracked changes and new untracked files alike — and reviews without seeing …

    line 17
  2. Distinctive:

    Only then does a synthesizer reconcile the findings.

    line 19
  3. Distinctive:

    Run it before opening a pull request, and again after any change to security-sensitive code.

    line 25
  4. Distinctive:

    Do not apply fixes unless you are asked to.

    line 53
  5. Distinctive:

    If you are reading this while acting as a peer in someone else's consultation, these instructions do not apply to you.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 4 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Managed by `model-peer init`. Version 0.8.1. Re-run `model-peer update` to refresh; local edits are replaced. -->

Cross-model review

You are Claude. Codex and Gemini review alongside you, independently.

model-peer review ["focus instructions"]

Every installed model receives the same Git status and patch — tracked changes and new untracked files alike — and reviews without seeing the others' conclusions. Only then does a synthesizer reconcile the findings. Reviewers are leaves by default: none of them consults another model, which is what makes agreement between them real signal rather than an echo.

Because they are independent, they also run at the same time.

Run it before opening a pull request, and again after any change to security-sensitive code.

model-peer review "Focus on authorization and tenant isolation"
model-peer review --models codex,gemini   # exclude yourself
model-peer review --timeout 300   # bound each reviewer, not the whole panel

It takes minutes. Let it finish, and do not be alarmed by how it looks while it runs:

  • Progress from several models arrives on stderr at once, interleaved, in a different order each run. That is normal.
  • Nothing appears on stdout until every reviewer has finished. The reviews are then printed together, in the order the models were requested. A long silence is the panel working, not a hang.

A reviewer that times out, fails, or returns nothing is dropped and named; synthesis needs two survivors and says so when the panel was incomplete.

What to do with the report

Report the synthesized findings as they are, grouped by severity. Then, for each one, say whether you agree and why. Reviewers do not know this project's invariants, so a finding that contradicts the rules in this repository is wrong here however sound it sounds in general.

Do not apply fixes unless you are asked to.

If you are reading this while acting as a peer in someone else's consultation, these instructions do not apply to you. Answer the question you were asked, and do not start a review of your own.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.