cr-multi

Automate parallel code reviews using Claude, Codex, and Gemini LLMs.

Updated Jun 3, 2026
One-click install
npx skills add https://github.com/moongci38-oss/forge-plugins --skill cr-multi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cr-multi
Source: https://github.com/moongci38-oss/forge-plugins/tree/main/forge-core/skills/cr-multi
Command: npx skills add https://github.com/moongci38-oss/forge-plugins --skill cr-multi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Claude Code, Codex, Gemini, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The cr-multi Skill automates and optimizes code review processes, allowing for efficient and thorough code audits without manual oversight.

Core Features & Use Cases

  • Parallel Code Review: Concurrent reviews from Claude, Codex, and Gemini using a triple or double worker setup.
  • Automated Triage: Integrates a triage phase for quick assessment and flagging of critical issues.
  • Security Checks: Performs pre-review secret scanning and security audits.
  • Use Case: Ideal for developers who need to conduct comprehensive code reviews efficiently, especially for critical and complex projects.

Quick Start

To perform a code review using cr-multi, run the following command: /cr-multi [path/to/your/code/file]

Frequently Asked Questions about cr-multi

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

FAQPage Schema
How do I automate code review with multiple LLMs at the same time?

To automate parallel code review, you can use a triple or double worker setup that concurrently runs Claude, Codex, and Gemini LLMs on your code files. This approach allows for comprehensive audits without manual oversight.

Can I run security scanning and triage before a full code review?

Yes, automated triage and security checks can run before a full code review. The process applies a triage phase for quick issue flagging and performs pre-review secret scanning to identify critical vulnerabilities early.

Does parallel code review work with Claude, Codex, and Gemini models?

Parallel code review works by concurrently utilizing Claude, Codex, and Gemini LLMs. This triple or double worker setup requires the Claude Code infrastructure and appropriate LLM models to execute automated audits.

How do I run an automated code audit on a specific file?

To run an automated code audit on a specific file, execute the command `/cr-multi [path/to/your/code/file]`. This triggers the parallel review process using the configured LLMs to analyze your code.

Do I need Claude Code infrastructure to perform automated LLM code reviews?

Yes, you need the Claude Code infrastructure and appropriate LLM models to perform automated parallel code reviews. This environment supports the concurrent execution of Claude, Codex, and Gemini for security checks and triage.

What is the best way to handle code reviews for complex software projects?

The best way to handle code reviews for complex software projects is through parallel LLM processing. Automating the review workflow with multiple LLMs provides efficient, thorough code audits and automated triage for critical issues.