skill-codex

Note: If you want a more autonomous setup for agentic workflows, check out klaudworks/ralph-meets-rex.

Codex Integration for Claude Code

Purpose

Enable Claude Code to invoke the Codex CLI (codex exec and session resumes) for automated code analysis, refactoring, and editing workflows.

Prerequisites

• codex CLI installed and available on PATH.
• Codex configured with valid credentials and settings.
• Confirm the installation by running codex --version; resolve any errors before using the skill.

Installation

This repository is structured as a Claude Code Plugin with a marketplace. You can install it as a plugin (recommended) or extract it as a standalone skill.

Option 1: Plugin Installation (Recommended)

Install via Claude Code's plugin system for automatic updates:

/plugin marketplace add skills-directory/skill-codex
/plugin install skill-codex@skill-codex

Option 2: Standalone Skill Installation

Extract the skill folder manually:

git clone --depth 1 git@github.com:skills-directory/skill-codex.git /tmp/skills-temp && \
mkdir -p ~/.claude/skills && \
cp -r /tmp/skills-temp/plugins/skill-codex/skills/codex ~/.claude/skills/codex && \
rm -rf /tmp/skills-temp

Usage

Important: Thinking Tokens

By default, this skill suppresses thinking tokens (stderr output) using 2>/dev/null to avoid bloating Claude Code's context window. If you want to see the thinking tokens for debugging or insight into Codex's reasoning process, explicitly ask Claude to show them.

Example Workflow

User prompt:

Use codex to analyze this repository and suggest improvements for my claude code skill.

Claude Code response: Claude will activate the Codex skill and:

1. Ask which model to use (gpt-6-astra by default; gpt-6.1-sol, gpt-6-sol, gpt-6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna; or a legacy model such as gpt-5.5, which ChatGPT-account sign-ins reject) unless already specified in your prompt.
2. Ask which reasoning effort level (low, medium, high, xhigh, max, or ultra, subject to the model's ceiling) unless already specified in your prompt.
3. Select appropriate sandbox mode (defaults to read-only for analysis)
4. Run a command like:

codex exec -m gpt-6-astra \
  --config model_reasoning_effort="high" \
  --sandbox read-only \
  "Analyze this Claude Code skill repository comprehensively..." 2>/dev/null

This example runs inside a Git repository. Apply the skip-flag permission gate.

Result: Claude will summarize the Codex analysis output, highlighting key suggestions and asking if you'd like to continue with follow-up actions.

Detailed Instructions

See plugins/skill-codex/skills/codex/SKILL.md for complete operational instructions, CLI options, and workflow guidance.