What models does it support for the review process?

It is designed to work with models supported by the Codex CLI, such as GPT-4 or GPT-5, allowing for high-reasoning depth and configuration via ~/.codex/config.toml.

What is the primary benefit of cross-model review?

Single-model self-review is often biased; using a different architecture like Codex helps catch blind spots that the original authoring model might miss during the development process.

Does this skill require external tools?

Yes, you must have the Codex CLI installed and authenticated on your system for this skill to function correctly.

Is this a total replacement for human peer review?

No, it is a powerful supplement that catches technical bugs and patterns. Human reviewers are still essential for evaluating product direction and user experience.

Can I use this for security-specific audits?

Absolutely. The skill includes a dedicated multi-pass strategy and 'exec' mode specifically designed for security concerns like OWASP Top 10, injection, and auth handling.

Codex Cross-Model Code Review

Name: Codex Cross-Model Code Review
Author: hyperb1iss

byhyperb1iss

•

협업 도구

Performs automated, cross-model code reviews using the Codex CLI to eliminate self-approval bias and catch complex bugs.

This skill enables Claude to conduct rigorous, multi-pass code reviews by leveraging the Codex CLI as an external validator. By using a secondary model architecture to review Claude’s output, it eliminates the systematic biases inherent in single-model self-reviews and catches a wider range of bug classes. It supports various review patterns, including pre-PR checks, security-focused deep dives, and iterative 'Ralph Loops,' ensuring high-quality, production-ready code through structured diff analysis and adjustable reasoning depth.

주요 기능

01Structured diff reviews with prioritized findings for PRs and commits

02Iterative 'Ralph Loop' pattern for continuous implementation and refinement

03Cross-model validation to eliminate LLM self-approval bias

04Deep-dive 'exec' mode for freeform investigation with high reasoning effort

05Multi-pass strategies for focused correctness, security, and architecture audits

062 GitHub stars

사용 사례

01Conducting security-focused audits on code touching authentication or APIs

02Performing work-in-progress (WIP) checks to find bugs before committing code

03Automating peer reviews for large pull requests to catch logic edge cases

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add hyperb1iss/hyperskills codex-review

For use in Claude.ai and ChatGPT

Download Skill