agentleFS
Sign inStart free
akasecurityakasecurity/preflight-skills/skills/crew-review/SKILL.md

crew-review

Skill1 starsChanged 4 months agoMITView on GitHub

Use when the user wants a second opinion on changes, a pre-merge review, or an independent multi-model read of a git commit range.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. badgids/Story-Film-Skills★ 4same name
    2. ypxing/coding-crew★ 1same name
    3. yilinwang0203-lab/crew-review-studio★ 0same 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 repository10 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

crew-review

Overview

Independent, multi-model review of a git diff. Report-only — it prints a report and never merges, fixes, or mutates anything; acting on the verdict is the user's separate decision. The review is produced by one script (crew.mjs): run the script. Do not perform the review yourself or spawn your own reviewer subagents. Your job is to run it and surface its report faithfully.

Usage

Require a git range: /crew-review <git-range> [--item <label>] [--read family[:tune] ...] [--judge family[:model]] [--timeout <sec>]

Resolve the script

The script lives at <this skill's base directory>/../../scripts/crew.mjs. Resolve it from the base directory the harness gives you for this skill — never guess or hardcode another location.

Run it

Echo the exact command, then run it from the current repo root:

node <resolved-path>/crew.mjs review <git-range> [flags…]

Families: claude · openai (codex CLI) · google (agy CLI). With no flags the script detects installed CLIs and prefers a cross-family crew automatically.

Tiers are fast / balanced / extra (aliases cheap / standard / most-capable); reviewers get balanced at minimum. For codex, read codex debug models, choose a model and effort by capability, and pass --read openai:<model>@<effort>; never copy a model id from a table or an old session.

After it finishes

  • Surface compactly: the anchor, the CREW composition line, each read's verdict and findings, and the judge's verdict with its discarded/systemic lists.
  • Preserve the report-only boundary: do NOT act on the verdict — no merge, no fix, no commit. Acting is the user's separate decision.
  • On exit 1/2, relay the stderr message verbatim (it names the missing CLI, bad range, or usage problem) AND surface any report that printed on stdout — an exit 1 with all reads skipped still prints a useful report there.
  • The run appends telemetry to ~/.preflight/modelcalls.jsonl and writes nothing into the reviewed repo.

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.

Check your setup, free