codex

Review code diffs with an independent pass/fail gate via OpenAI Codex CLI.

Updated Mar 31, 2026

Search Tags:#cli #codex #ai-assistant #code-review #diff-review #second-opinion

Ready to run

npx skills add https://github.com/huichen/gstack --skill codex-huichen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codex
Source: https://github.com/huichen/gstack/tree/main/codex
Command: npx skills add https://github.com/huichen/gstack --skill codex-huichen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides an independent, honest second opinion on code changes by wrapping the OpenAI Codex CLI, helping catch issues before shipping.

Core Features & Use Cases

Review: independent diff review with a pass/fail gate.
Challenge: adversarial mode that tries to break your code.
Consult: ask Codex anything with session continuity for follow-ups.
Use case: verify critical changes across diffs, plans, and prompts.

Quick Start

Run /codex review to get an independent assessment of your current changes.

Frequently Asked Questions about codex

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

FAQPage Schema

How do I get an independent AI code review for my git diff before shipping?▼

To get an independent AI code review, you can run the review mode on your current changes to receive a pass/fail gate assessment. This provides an honest second opinion on your code changes by wrapping the OpenAI Codex CLI.

Can I use an AI assistant to challenge and try to break my code changes?▼

Yes, you can use the challenge mode to adversarially test your code changes. This mode forces the AI assistant to try and break your code, helping catch vulnerabilities and edge cases before deployment.

What is the best way to consult an AI assistant for continuous follow-up questions on a code plan?▼

The best way to consult an AI assistant with session continuity is by using the consult mode. This allows you to ask questions about diffs, plans, and prompts while maintaining session context for follow-up inquiries.

Does the Codex CLI code review support integration into existing Git workflows?▼

Yes, the Codex CLI code review supports direct integration into your Git workflow. It processes diffs, plans, and prompts to output structured results suitable for plans and dashboards.

How can I route controls and toggle telemetry for an AI code review session?▼

You can configure routing controls and toggle telemetry settings during your AI code review session. The system enforces safe usage by allowing you to manage these configurations directly.

When should I use an adversarial challenge mode instead of a standard code diff review?▼

You should use adversarial challenge mode instead of a standard diff review when verifying critical changes. It actively tries to break your code, whereas the standard review mode provides an independent pass/fail assessment.