Codex

Codex Skill Guide

Running a Task

1. Default to gpt-5.2 model. Ask the user (via AskUserQuestion) which reasoning effort to use (xhigh,high, medium, or low). User can override model if needed (see Model Options below). 2. Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary. 3. Assemble the command with the appropriate options:

• -m, --model <MODEL>
• --config model_reasoning_effort="<high|medium|low>"
• --sandbox <read-only|workspace-write|danger-full-access>
• --full-auto
• -C, --cd <DIR>
• --skip-git-repo-check

3. Always use --skip-git-repo-check. 4. When continuing a previous session, use codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort when requesting to resume a session. Resume syntax: echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null. All flags have to be inserted between exec and resume. 5. IMPORTANT: By default, append 2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed. 6. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user. 7. After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes."

Quick Reference

Model Options

GPT-5.2 Advantages: 76.3% SWE-bench (vs 72.8% GPT-5), 30% faster on average tasks, better tool handling, reduced hallucinations, improved code quality. Knowledge cutoff: September 30, 2024.

Reasoning Effort Levels:

• xhigh - Ultra-complex tasks (deep problem analysis, complex reasoning, deep understanding of the problem)
• high - Complex tasks (refactoring, architecture, security analysis, performance optimization)
• medium - Standard tasks (refactoring, code organization, feature additions, bug fixes)
• low - Simple tasks (quick fixes, simple changes, code formatting, documentation)

Cached Input Discount: 90% off ($0.125/M tokens) for repeated context, cache lasts up to 24 hours.

Following Up

• After every codex command, immediately use AskUserQuestion to confirm next steps, collect clarifications, or decide whether to resume with codex exec resume --last.
• When resuming, pipe the new prompt via stdin: echo "new prompt" | codex exec resume --last 2>/dev/null. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.
• Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.

Error Handling

• Stop and report failures whenever codex --version or a codex exec command exits non-zero; request direction before retrying.
• Before you use high-impact flags (--full-auto, --sandbox danger-full-access, --skip-git-repo-check) ask the user for permission using AskUserQuestion unless it was already given.
• When output includes warnings or partial results, summarize them and ask how to adjust using AskUserQuestion.

CLI Version

Requires Codex CLI v0.57.0 or later for GPT-5.2 model support. The CLI defaults to gpt-5.2 on macOS/Linux and gpt-5.2 on Windows. Check version: codex --version

Use /model slash command within a Codex session to switch models, or configure default in ~/.codex/config.toml.

Leave a star ⭐ if you like it 😘

Codex Integration for Claude Code

<img width="2288" height="808" alt="skillcodex" src="https://github.com/user-attachments/assets/85336a9f-4680-479e-b3fe-d6a68cadc051" />

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

Download this repo and store the skill in ~/.claude/skills/codex

git clone --depth 1 git@github.com:skills-directory/skill-codex.git /tmp/skills-temp && \
mkdir -p ~/.claude/skills && \
cp -r /tmp/skills-temp/ ~/.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-5 or gpt-5-codex) unless already specified in your prompt. 2. Ask which reasoning effort level (low, medium, or high) 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-5-codex \
  --config model_reasoning_effort="high" \
  --sandbox read-only \
  --full-auto \
  --skip-git-repo-check \
  "Analyze this Claude Code skill repository comprehensively..." 2>/dev/null

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 SKILL.md for complete operational instructions, CLI options, and workflow guidance.