codex

Review code changes, implementation plans, or specific files using OpenAI Codex CLI. Triggers on "review", "check", "validate", "codex". Perfect for maker-checker workflows where you want a second AI agent to review Claude's work before committing. Requires the Codex CLI to be installed (brew install codex-cli or from https://codex.storage.googleapis.com).

8 stars

byadampaulwalker

View on GitHub Installation ↓

Best use case

codex is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using codex should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

How codex Compares

Feature / Agent	codex	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

Cursor vs Codex for AI Workflows

Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

SKILL.md Source

# Codex Code Review Skill

**Version:** 1.0.0
**Author:** Community-contributed
**Requires:** [Codex CLI](https://codex.storage.googleapis.com) installed and configured

## Overview

Use the Codex CLI to perform independent code reviews on changes made during your Claude Code session. This enables a "proposer-checker-maker-checker" workflow where Claude Code proposes/implements changes and Codex provides an independent review.

## Prerequisites

Install the Codex CLI:
```bash
brew install codex-cli
# OR download from https://codex.storage.googleapis.com
```

Configure your OpenAI API key:
```bash
codex login
```

## Use the Codex CLI to review recent changes, implementation plans, or specific files.

## Review Recent Git Changes

```bash
# Review uncommitted changes
codex review "Review the uncommitted changes in this repo"

# Review specific commit
codex review "Review the changes in commit <hash>"

# Review changes between branches
codex review "Review the diff between main and current branch"
```

## Review Specific Files

```bash
# Review a specific file
codex review "Review the code in <file_path>"

# Review multiple files
codex review "Review the implementation in <file1> and <file2>"
```

## Review Implementation Plan

```bash
# Review a plan before implementation
codex review "Review this implementation plan: <plan_content>"
```

## Usage Pattern

1. Identify what needs review (recent changes, specific files, or a plan)
2. Run `codex review` with appropriate prompt
3. Present the review results to the user

The `codex review` command runs non-interactively and returns feedback that can be incorporated into the Claude Code session.

## Workflow Example

```
User: I just implemented user authentication
Claude: [implements auth.ts, auth-middleware.ts, etc.]
User: /codex
Claude: [runs: codex review --uncommitted]
Claude: Codex found 2 issues:
  1. Missing error handling in auth.ts:45
  2. Password hash strength could be improved
User: Fix those issues
Claude: [fixes issues]
User: /codex
Claude: [runs review again]
Claude: Codex approves! No issues found.
```

## Notes

- Works best in git repositories
- Review results are shown inline in the Claude Code session
- Combines well with Claude's implementation capabilities for a robust development workflow

Related Skills

Ralph Codex — OpenClaw Plugin

from joelhooks/openclaw-codex-ralph

Autonomous AI coding loops using Codex CLI. Spawn fresh AI sessions for each task, validate with tests, commit on success, repeat until done. 26 tools.

update-Codex-documentation

from peterbamuhigire/skills-web-dev

Update project documentation files (README.md, PROJECT_BRIEF.md, TECH_STACK.md, ARCHITECTURE.md, docs/API.md, docs/DATABASE.md, AGENTS.md, docs/plans/NEXT_FEATURES.md) when significant changes occur. MANDATORY at end of each work session to...

codex-cli

from creator-hian/claude-code-plugins

OpenAI Codex CLI fundamentals for code analysis, review, and validation. Use when (1) executing codex commands for code review/analysis, (2) configuring models (gpt-5.3-codex/gpt-5.2/gpt-5.1-codex-max/gpt-5-codex-mini), sandbox modes (read-only/workspace-write), or reasoning effort (low/medium/high/xhigh), (3) managing Codex sessions with resume, (4) integrating Codex into automation scripts. Do NOT use for orchestration patterns (use codex-claude-loop instead).

codex-claude-loop

from creator-hian/claude-code-plugins

Dual-AI engineering loop orchestrating Claude Code (planning/implementation) and Codex (validation/review). Use when (1) complex feature development requiring validation, (2) high-quality code with security/performance concerns, (3) large-scale refactoring, (4) user requests codex-claude loop or dual-AI review. Do NOT use for simple one-off fixes or prototypes.

emergence-codex

from Demerzels-lab/elsamultiskillagent

Semantic Architecture Language to Combat the Smoothing Anathema

openai-codex-operator

from Demerzels-lab/elsamultiskillagent

Run OpenAI Codex CLI from OpenClaw for coding tasks in a target project directory.

secretcodex

from Demerzels-lab/elsamultiskillagent

Generate creative code names and encode/decode secret messages using classic and sophisticated ciphers.

codex-cli

from Demerzels-lab/elsamultiskillagent

Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.

codex-cli-invoke-persist

from igamenovoer/magic-context

Create and resume Codex CLI sessions with a persistent session-name-to-thread_id mapping plus last-used model stored in a workspace-scoped JSON file under system temp. Invoke only when the user explicitly names `$codex-cli-invoke-persist` or otherwise clearly requests this exact skill. Use it for deterministic, session-persistent Codex automation across turns and processes.

codex-cli-invoke-once

from igamenovoer/magic-context

Programmatically invoke Codex via the `codex` CLI for headless, non-interactive runs using `codex exec`, machine-readable JSONL via `--json`, final-message capture via `-o/--output-last-message`, and multi-turn continuation via `codex exec resume`. Use when you need scriptable Codex automation for repo reviews, issue investigation, implementation planning, or structured one-shot outputs.

codex-cli-install

from igamenovoer/magic-context

A three-part Codex CLI setup skill with subskills for installation, skip-login configuration, and custom API-key launcher setup. Use when the user wants Codex CLI installed or configured on the current host, with instructions adapted to the actual operating system and runtime environment.

codex-review

from ifokeev/airbrowser-mcp

Run OpenAI Codex code review on current changes or review a plan/design. Use when user asks to review code, review implementation, or run codex review.