How do I install the Review Codex Plan skill?

Run npx skillmds add zirui-song/review-codex-plan in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Codex Plan safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Codex Plan?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Codex Plan free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Codex Plan?

zirui-song (@zirui-song) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Codex Plan by zirui-song — Agent Skill

Name: Review Codex Plan
Rating: 4.2 (5 reviews)
Author: zirui-song

Review Codex Plan

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".

zirui-song 363bbdf 2.3 KB Updated Sep 10, 2026

File contents

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

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.
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.
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.

---name: review-codex-plandescription: 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".---# 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.## Workflow1. **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: ```bash 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.

Frequently asked questions