codex

Review, challenge, or consult on code changes using the Codex CLI.

1|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/geoffreywoo/clawfable --skill codex-geoffreywoo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/geoffreywoo/clawfable/tree/main/.claude/skills/gstack/codex
Command: npx skills add https://github.com/geoffreywoo/clawfable --skill codex-geoffreywoo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides an independent, brutally honest second opinion on code changes using the Codex CLI to supplement or replace traditional human gates.

Core Features & Use Cases

  • Three modes: review for deterministic code review gating, challenge for adversarial testing, and consult for ad-hoc questions with session continuity.
  • Reads diffs and project context to generate actionable feedback that helps ships safer code faster.
  • Use cases include pre-merge audits, security-focused prompts, and real-time Q&A while coding.

Quick Start

Run /codex review to start a formal code review or /codex challenge to test adversarial changes.

Frequently Asked Questions about codex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is adversarial code testing and how does it challenge my changes?

Adversarial code testing is performed using the challenge mode, which prompts the Codex CLI to aggressively test changes against edge cases and security vulnerabilities in your diffs.

Do I need the Codex CLI installed to run code reviews and analyze diffs?

Ad-hoc coding questions are handled in consult mode, which allows real-time Q&A while preserving session context across multiple interactions for continuous analysis.

What's the best way to automate a pre-merge security audit for code changes?

The Codex CLI must be installed and ready to analyze diffs, gate outcomes, and preserve context across interactions before you can execute review, challenge, or consult commands.

Why does my code review need an independent AI gatekeeper?

A pre-merge security audit is automated by running the challenge mode to apply adversarial prompts against your code changes, generating brutally honest feedback to supplement human gates.

When should I not rely on an AI code review for my project?

An independent AI gatekeeper supplements traditional human gates by delivering unbiased, brutally honest feedback on code changes, helping you ship safer code faster without emotional bias.