Codex Skill

Codex Skill for Claude Code

Give Claude Code a "second opinion" by letting it consult OpenAI's Codex CLI for independent verification.

What It Does

When Claude Code creates a plan, Codex automatically reviews it before you approve. Two AIs checking each other's work catches more edge cases.

Automatic review on:
- Every plan Claude creates (via hook)
- Architecture decisions
- Implementation approaches

Manual use for:
- Researching unfamiliar APIs or libraries
- Verifying complex code patterns
- Getting alternative perspectives

Prerequisites

Install Codex CLI:

Configure your OpenAI API key.

Supported Models

The skill supports the current visible Codex lineup. Automatic plan reviews do not pin a model; they inherit your configured Codex default.

gpt-5.6-sol, gpt-5.6-terra and gpt-5.6-luna are still listed as older generations.

Installation

Option A: Install as Claude Code plugin (recommended)

This auto-registers both the /codex skill and the automatic plan review hook. No manual configuration needed.

Option B: Manual installation

1. Install the skill

2. Set up automatic plan review

Copy the hook script:

Add to your ~/.claude/settings.json:

How It Works

The hook intercepts ExitPlanMode and reads the plan from tool_response.plan (the field where Claude Code stores the plan content). It passes the plan to Codex for review and displays the result before you approve.

Automatic plan reviews always use codex exec --sandbox read-only to restrict model-generated shell commands to read-only access. Manual consultations default to the same mode; explicit requests to implement changes use --sandbox workspace-write. If Codex fails, the hook reports that the review was skipped on stderr and exits successfully so your workflow can continue.

Codex reviews for:
-…