agentleFS
Sign inStart free
zirui-songzirui-song/claude-skills/skills/review-codex-plan/SKILL.md

review-codex-plan

Skill17 starsChanged 3 months agoMITView on GitHub

Use to have Claude critically review a Codex-authored implementation plan against the real codebase — or to have Codex draft a plan for a task first and then review it. The reverse of codex-review-plan. Trigger phrases include "review this Codex plan", "have Codex draft a plan then check it", "what's wrong with Codex's plan".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Output: Write the full critique to a temp file (or the plan file if you're producing a Claude-improved version), and summarize in ≤10 lines …

    line 32
  2. Distinctive:

    Verify before you agree or disagree — ground every point in the actual code, not in plausibility.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

review-codex-plan (Codex → Claude)

The "vice versa" direction: Claude rigorously reviews a plan that Codex wrote. Either you supply the Codex plan, or this skill asks Codex to draft one first, then Claude critiques it against the actual code.

Mechanics (wrapper, drafting template, timeout, output rules) live in the codex-bridge skill — read it first.

Workflow

  1. Get the Codex plan. Two paths:
    • (a) Supplied — the user gives a plan file or pasted text. Use it directly.
    • (b) Generate — the user gives only a task. Use the drafting template from codex-bridge and run the wrapper to have Codex produce the plan:
      OUT=/tmp/codex-drafted-plan-$$.md
bash ~/.claude/skills/codex-bridge/codex-exec.sh "$PROJECT_DIR" "$OUT" < "$PROMPT_FILE"
      (Long Bash timeout ~600000 ms.) The drafted plan lands in $OUT.
  2. Review it rigorously as Claude. Read the relevant files, trace the code, and verify each of Codex's claims/assumptions against reality. Apply the same reviewer rubric used in codex-bridge: wrong assumptions, missing steps/edge cases, risky changes, simpler reuse-existing-code approaches, and what's right.
  3. Output. Write the full critique to a temp file (or the plan file if you're producing a Claude-improved version), and summarize in ≤10 lines in chat:
    • Strengths (brief).
    • Concrete issues, each with a file:line reference.
    • Missing steps / risks.
    • A Claude-improved version of the plan (or a pointer to where you wrote it).

Notes

  • Codex runs read-only when drafting; it cannot modify your files.
  • Verify before you agree or disagree — ground every point in the actual code, not in plausibility. If Codex's plan is mostly sound, say so; don't manufacture objections.
  • To run a full back-and-forth between the two models, use the plan-debate skill instead.

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