cross-review-policy

Enforces Codex review of AI-generated commits with iteration limits and standardized messaging.

1|1|Updated Nov 1, 2022
One-click install
npx skills add https://github.com/vamseeachanta/assethold --skill cross-review-policy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cross-review-policy
Source: https://github.com/vamseeachanta/assethold/tree/main/.claude/skills/workflows/cross-review-policy
Command: npx skills add https://github.com/vamseeachanta/assethold --skill cross-review-policy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enforces a formal cross-review workflow for AI-generated work, ensuring that every code or artifact produced by Claude/Gemini is reviewed by OpenAI Codex before user delivery.

Core Features & Use Cases

  • Policy enforcement: Requires a codex-based review on AI-generated commits.
  • Iteration controls: Limits review cycles to a defined maximum with structured feedback.
  • Use Case: A development team wants to ensure all AI-assisted changes go through a Codex review before deployment in CI/CD.

Quick Start

Run the cross-review loop to start a review on a new change: ./scripts/ai-review/cross-review-loop.sh --max-iterations 3 Then check progress with: ./scripts/ai-review/review-manager.sh list

Frequently Asked Questions about cross-review-policy

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

FAQPage Schema
How do I enforce a cross-review policy for AI-generated code commits?

You can enforce a cross-review policy for AI-generated code commits by running the cross-review loop script, which requires OpenAI Codex to review all outputs before user delivery. It applies to code and documentation across development workflows.

What is a cross-review workflow for AI-assisted development?

A cross-review workflow for AI-assisted development ensures that every artifact produced by an AI like Claude or Gemini is reviewed by OpenAI Codex. It satisfies defined review sequencing, maximum iterations, and standardized commit messaging.

How do I limit review iterations for AI code tasks in a CI/CD pipeline?

You can limit review iterations for AI code tasks by running the cross-review loop script with the max-iterations flag, such as setting it to 3. This limits review cycles to a defined maximum with structured feedback.

Can I use a cross-review policy to standardize AI commit messaging?

Yes, applying a cross-review policy for AI-generated work enforces standardized commit messaging alongside defined review sequencing. It ensures all AI-driven commits and reviews follow a consistent format across development workflows.

Does the cross-review policy work for AI-generated documentation as well as code?

Yes, the cross-review policy applies to all AI-driven commits and reviews across development workflows, including both code and documentation. It ensures Codex-review of all outputs before user delivery.