Skip to content
Back to search

skill-codex

Marketplace for the skill-codex plugin, enabling Claude Code to delegate tasks to OpenAI Codex CLI

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/skills-directory-skill-codex/badge.svg)](/listings/skills-directory-skill-codex)

HTML

<a href="/listings/skills-directory-skill-codex"><img src="/api/listings/skills-directory-skill-codex/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

This repository is structured as a [Claude Code Plugin](https://code.claude.com/docs/en/plugins) 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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 25 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "skill-codex",
  4. "description": "Marketplace for the skill-codex plugin, enabling Claude Code to delegate tasks to OpenAI Codex CLI",
  5. "owner": {
  6. "name": "skills-directory",
  7. "url": "https://github.com/skills-directory"
  8. },
  9. "plugins": [
  10. {
  11. "name": "skill-codex",
  12. "source": "./plugins/skill-codex",
  13. "description": "Delegate prompts to OpenAI Codex CLI for code analysis, refactoring, code review, and automated editing",
  14. "version": "1.3.1",
  15. "category": "development",
  16. "homepage": "https://github.com/skills-directory/skill-codex",
  17. "tags": [
  18. "skill",
  19. "codex",
  20. "automation",
  21. "code-review"
  22. ]
  23. }
  24. ]
  25. }
README.md · README · 70 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. Note: If you want a more autonomous setup for agentic workflows, check out [klaudworks/ralph-meets-rex](https://github.com/klaudworks/ralph-meets-rex).
  2. # Codex Integration for Claude Code
  3. <img width="2288" height="808" alt="skillcodex" src="https://github.com/user-attachments/assets/85336a9f-4680-479e-b3fe-d6a68cadc051" />
  4. ## Purpose
  5. Enable Claude Code to invoke the Codex CLI (`codex exec` and session resumes) for automated code analysis, refactoring, and editing workflows.
  6. ## Prerequisites
  7. - `codex` CLI installed and available on `PATH`.
  8. - Codex configured with valid credentials and settings.
  9. - Confirm the installation by running `codex --version`; resolve any errors before using the skill.
  10. ## Installation
  11. This repository is structured as a [Claude Code Plugin](https://code.claude.com/docs/en/plugins) with a marketplace. You can install it as a **plugin** (recommended) or extract it as a **standalone skill**.
  12. ### Option 1: Plugin Installation (Recommended)
  13. Install via Claude Code's plugin system for automatic updates:
  14. ```
  15. /plugin marketplace add skills-directory/skill-codex
  16. /plugin install skill-codex@skill-codex
  17. ```
  18. ### Option 2: Standalone Skill Installation
  19. Extract the skill folder manually:
  20. ```
  21. git clone --depth 1 git@github.com:skills-directory/skill-codex.git /tmp/skills-temp && \
  22. mkdir -p ~/.claude/skills && \
  23. cp -r /tmp/skills-temp/plugins/skill-codex/skills/codex ~/.claude/skills/codex && \
  24. rm -rf /tmp/skills-temp
  25. ```
  26. ## Usage
  27. ### Important: Thinking Tokens
  28. 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.
  29. ### Example Workflow
  30. **User prompt:**
  31. ```
  32. Use codex to analyze this repository and suggest improvements for my claude code skill.
  33. ```
  34. **Claude Code response:**
  35. Claude will activate the Codex skill and:
  36. 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.
  37. 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.
  38. 3. Select appropriate sandbox mode (defaults to `read-only` for analysis)
  39. 4. Run a command like:
  40. ```bash
  41. codex exec -m gpt-6-astra \
  42. --config model_reasoning_effort="high" \
  43. --sandbox read-only \
  44. "Analyze this Claude Code skill repository comprehensively..." 2>/dev/null
  45. ```
  46. This example runs inside a Git repository. Apply the [skip-flag permission gate](plugins/skill-codex/skills/codex/SKILL.md#running-a-task).
  47. **Result:**
  48. Claude will summarize the Codex analysis output, highlighting key suggestions and asking if you'd like to continue with follow-up actions.
  49. ### Detailed Instructions
  50. See [`plugins/skill-codex/skills/codex/SKILL.md`](plugins/skill-codex/skills/codex/SKILL.md) for complete operational instructions, CLI options, and workflow guidance.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.