Cmd Codex Review Unstaged

Get a second opinion on what Claude just implemented from Codex (codex exec headless mode). Pipes Claude's summary plus the working-tree diff to codex, asks codex to leverage cmd-pr-follow-up and cmd-pr-edgecase methodology to surface bugs, test gaps, edge cases, and simplification opportunities, then synthesizes a prioritized iteration plan from the feedback. Triggers on "/cmd-codex-review-unstaged", "review my changes with codex", "have codex review what I just did", or after a non-trivial implementation pass before commit.

9 starsSoftware Development Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Olshansk/agent-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Olshansk/agent-skills --skill cmd-codex-review-unstaged
Manual install
git clone --depth 1 https://github.com/Olshansk/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/cmd-codex-review-unstaged ~/.claude/skills/cmd-codex-review-unstaged

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Codex Review Unstaged 

Use `codex exec` as an independent reviewer on the working-tree changes Claude just made. Codex sees only the summary + diff (no conversation history), so its critique catches things Claude rationalized into "good enough" during implementation. The output is a prioritized iteration plan — what to fix now, what to defer, what to reject.

- [When to use](#when-to-use)
- [Instructions](#instructions)
- [Codex prompt](#codex-prompt)
- [Output format](#output-format)
- [Notes](#notes)

## When to use

- After Claude finishes a non-trivial implementation pass and before commit
- When the user says "review my changes with codex", "have codex check what I just did", or `/cmd-codex-review-unstaged`
- As an outside cross-check before opening a PR — complements `cmd-pr-follow-up` (Claude self-review) and `cmd-pr-edgecase` (edge-case sweep) by adding a fresh pair of eyes that didn't write the code

## Instructions

### 1. Build Claude's implementation summary

Write a short summary of what was just implemented. Keep it **factual, not promotional**:

- What was the goal?
- What files changed and why?
- What design decisions were made (and what was rejected)?
- What was deliberately deferred (TODOs, follow-ups, scope cuts)?
- What was tested manually vs. covered by automated tests?

This summary anchors codex's review — without it, codex will judge the diff against a generic standard instead of the actual intent.

### 2. Capture the diff
Read the full skill on GitHub

Details

Skill name
cmd-codex-review-unstaged
Path
skills/cmd-codex-review-unstaged/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Cmd Codex Review Unstaged skill do?

Get a second opinion on what Claude just implemented from Codex (codex exec headless mode). Pipes Claude's summary plus the working-tree diff to codex, asks codex to leverage cmd-pr-follow-up and cmd-pr-edgecase methodology to surface bugs, test gaps, edge cases, and simplification opportunities, then synthesizes a prioritized iteration plan from the feedback. Triggers on "/cmd-codex-review-unstaged", "review my changes with codex", "have codex review what I just did", or after a non-trivial implementation pass before commit.

How do I install the Cmd Codex Review Unstaged skill?

Claude Code plugin: /plugin marketplace add Olshansk/agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cmd Codex Review Unstaged popular?

It lives in Olshansk/agent-skills, which has 9 GitHub stars and 0 forks.

Related skills

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.