agentleFS
Sign inStart free
timursafiullintimursafiullin/aod/skills/cross-review/SKILL.md

cross-review

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Have Codex (another model family) review changes the architect wrote itself - UI, security core, quick fixes - before they are committed or merged. Use whenever Claude, not a delegated implementer, wrote the code.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use unslop and handoff.

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.
  • photon-groveSkill

    unslop

    Detects and rewrites generic, overly polished, or AI-sounding prose while preserving meaning. Use when the user asks to "unslop", humanize, de-AI, tighten, or review whether writing sounds generated.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 0

    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
  1. Very specific:

    Add --focus "<what matters most>" for security-core or tricky logic.

    line 15
  2. Very specific:

    Run it as a background shell command.

    line 16

“Common” is measured: kept by at least 6 in 10 of the 19 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

Cross-family review of the architect's own changes

Delegated work is reviewed by gates plus the aod:reviewer subagent. Code you wrote yourself gets a reviewer from another family. CLI: aod means node "${CLAUDE_PLUGIN_ROOT}/scripts/aod.mjs".

  1. Pick the target:
    • a branch: aod review --base <base branch> (default: the configured base branch);
    • one commit: aod review --commit <sha>;
    • work not committed yet: aod review --uncommitted. Add --focus "<what matters most>" for security-core or tricky logic.
  2. Run it as a background shell command; it can take several minutes. The full review is saved under .agents/tasks/jobs/reviews/, and the result lists the F<n> [severity] findings.
  3. Fix every blocker and major finding, or record in the journal why it does not apply. Re-run the review after substantial fixes.
  4. Exit code 5 means Codex is unavailable or out of quota: stop and ask the user (/aod:decision). Do not substitute a same-family review without saying so.

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