agentleFS
KenmegeKenmege/codex-claude-companion/skills/claude-review/SKILL.md

claude-review

Skill2 starsChanged 6 months agoApache-2.0View on GitHub

Use when the user asks Codex to orchestrate Claude for a coding job in another terminal, or to review code, run adversarial or ship/no-ship review, audit security risks, or inspect a large diff/folder.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 more.

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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the local helper to route the requested Claude lane.

    line 8
  2. Distinctive:

    Keep review workflows read-only.

    line 35
  3. Very specific:

    Treat trusted-autonomous as explicit cooperative same-UID host trust, not a sandbox.

    line 39
  4. Distinctive:

    If the helper exits non-zero, report the exact failure and stop.

    line 44

“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

Claude Review

Use the local helper to route the requested Claude lane. New coding work uses a durable tmux-owned bridge worker with recorded collaboration, recovery, delivery, and independent verification. The older workspace lane remains available for compatibility. Review lanes snapshot the target, use read-only agentic mode, validate structured output, and render the result.

Default command

codex-claude review -- "$ARGUMENTS"

Route by intent

  • Coding or implementation: codex-claude delegate --verify-command '<JSON argv>' -- "$ARGUMENTS"; keep the active Codex task responsive and supervise the returned ccb_... job with wait, status, logs, send, and recover.
  • Legacy interactive workspace: codex-claude workspace -- "$ARGUMENTS"; use workspace-status, workspace-logs, and workspace-stop.
  • Everyday diff review: codex-claude review -- "$ARGUMENTS"
  • Release gate / ship-no-ship: codex-claude review --preset ship -- "$ARGUMENTS"
  • Security review: codex-claude review --preset security -- "$ARGUMENTS"
  • Research or evidence-heavy folder: codex-claude folder <path> --preset research --long-context -- "$ARGUMENTS"
  • Deep multi-agent review: codex-claude review --preset deep --background -- "$ARGUMENTS"

Operating rules

  • Keep review workflows read-only. Use a writable bridge or workspace lane only when the user asks for coding or implementation.
  • Require an origin-supplied repository-native verification command for every delegation. Do not accept a worker-chosen command as independent verification.
  • Treat trusted-autonomous as explicit cooperative same-UID host trust, not a sandbox. Never claim sandbox-autonomous is available.
  • The bridge may launch ephemeral Codex for independent verification. Do not hardcode a GPT model or claim the worker verified itself independently.
  • Return the helper output verbatim.
  • If the helper exits non-zero, report the exact failure and stop.
  • For first-run problems, ask the user to run codex-claude enable and codex-claude doctor.

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.