codex

Wrap OpenAI Codex CLI with code review, adversarial challenge, and consult modes.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/scanbott/claude-skills --skill codex-scanbott
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/scanbott/claude-skills/tree/main/gstack/codex
Command: npx skills add https://github.com/scanbott/claude-skills --skill codex-scanbott

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenAI Codex CLI wrapper that exposes three modes: code review, adversarial challenge, and consult, with session continuity for follow-ups.

Core Features & Use Cases

  • Code review: independent diff review via codex review with pass/fail gate.
  • Adversarial challenge: adversarial mode that tries to break your code.
  • Consult: ask codex anything with session continuity for follow-ups.
  • Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".

Quick Start

Run codex review to start an independent code review session.

Frequently Asked Questions about codex

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

FAQPage Schema
How do I run an independent code review on my diff using a CLI?

To start a code review using the CLI, execute the review command to trigger an independent diff evaluation with a pass/fail gate. This provides a rigorous evaluation of your changes before integration.

What is adversarial code testing and how does it stress test my logic?

Adversarial code testing is a mode that actively tries to break your code to expose hidden flaws. By challenging your logic under stress, it reveals vulnerabilities and edge cases during the development process.

Can I ask Codex questions and maintain session continuity for follow-ups?

Yes, you can consult Codex interactively while maintaining session continuity for follow-up queries. This preserves conversational context across multiple prompts during your development workflow.

Does the Codex CLI wrapper support voice triggers for code review and consultation?

Yes, the Codex CLI wrapper supports voice triggers via speech-to-text aliases like "code x" or "get another opinion". This enables hands-free routing into code review, adversarial challenge, or consult modes.

What are the limitations of using an adversarial challenge mode for code evaluation?

A limitation of adversarial challenge mode is that it specifically stress tests your code to break it, rather than providing standard best-practice feedback. It should be used alongside standard code review for safe, repeatable interactions.