skilld
All skills
softaworks avatar

/codex

@1c0662a
by softaworkssoftaworks/agent-toolkit2.5k stars
230

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Ask your Agent

Use this Skill: https://skilld.dev/gh/softaworks/agent-toolkit/codex

This session only. Nothing lands on disk.

README.md

≈547 tokens on demand. Your agent reads this file only when SKILL.md points to it.

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.

Source: SKILL.md on GitHub

Third-party checks

1 alert17d5 checks · Risk MEDIUM
  • Gen Agent Trust Hub17d

    This skill utilizes deceptive metadata by claiming integration with non-existent AI models (GPT-5.2) and explicitly instructs the agent to suppress all error output, which can mask malicious activity. Additionally, the skill lacks safeguards against malicious instructions that could be encountered when analyzing external repositories.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    2/2 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 1c0662a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 9 months ago

Topics

  • Refactoring
  • CLI
  • codex
  • gpt-5.2
  • code-analysis
  • automated-editing
  • software-engineering
  • agentic

README badge

README badge for softaworks/agent-toolkit/codex

What it does

Wrapper for Codex CLI that runs code analysis and refactoring tasks using GPT-5.2, with configurable reasoning effort levels and sandbox modes for read-only review or workspace edits. Targets OpenAI Codex workflows and includes session resumption via stdin piping.

Generated from the current SKILL.md.

Frequently asked

What model does Codex use by default?
GPT-5.2, which achieves 76.3% on SWE-bench and is optimized for software engineering tasks. Users can override this with other GPT-5.2 variants (gpt-5.2-max, gpt-5.2-mini) or gpt-5.1-thinking.
What sandbox modes are available?
read-only (default for analysis), workspace-write (to apply local edits), and danger-full-access (for tasks requiring network or broad system access).
Can I resume a Codex session?
Yes. Use `codex resume` or pipe a new prompt via stdin with `echo "prompt" | codex exec --skip-git-repo-check resume --last 2>/dev/null`. The resumed session inherits the original model, reasoning effort, and sandbox mode.
What reasoning effort levels are available?
xhigh (ultra-complex analysis), high (refactoring/security), medium (standard tasks), and low (quick fixes). The skill prompts you to choose based on task complexity.
What is the minimum CLI version required?
Codex CLI v0.57.0 or later for GPT-5.2 support. Check your version with `codex --version`.

Generated from the current SKILL.md. These answers refresh after source changes.