prp-review-agents

Automate parallel code, security, and quality review of pull request commits.

2|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/gobikom/prp-framework --skill prp-review-agents
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prp-review-agents
Source: https://github.com/gobikom/prp-framework/tree/main/adapters/codex/prp-review-agents
Command: npx skills add https://github.com/gobikom/prp-framework --skill prp-review-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the problem of thorough and efficient code reviews in PRs by leveraging multiple specialized agents that operate in parallel.

Core Features & Use Cases

  • Multi-Agent Parallel Review: Spawns parallel agents for code, security, error handling, and more.
  • Deep Code Exploration: Each agent has a fresh context window and deep file exploration capabilities.
  • Aspect-Specific Agents: Specialized agents for code quality, security, and performance, among others.
  • Incremental Review: Supports reviewing only the changes made since the last review, improving efficiency.
  • Large PR Handling: Categorizes files by risk tier and applies phased review strategy for PRs larger than 1000 lines.
  • Review Metrics: Provides detailed metrics on the findings and impact of the review.

Quick Start

/prp-review-agents $PR_NUMBER

Frequently Asked Questions about prp-review-agents

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

FAQPage Schema
How do I automate multi-agent code review for pull requests?

Automated multi-agent code review for pull requests is executed by spawning parallel specialized agents to analyze code, security, and quality aspects simultaneously. You simply provide the Git PR number to initiate the comprehensive review process.

Can I review only incremental code changes since the last PR review?

Incremental code review is supported to analyze only the changes made since the last review. This feature improves efficiency by skipping previously reviewed code and focusing solely on new commits within the pull request.

What is the best way to handle large PR code reviews exceeding 1000 lines?

Large PR code reviews exceeding 1000 lines are handled by categorizing files into risk tiers and applying a phased review strategy. This ensures thorough analysis without overwhelming the agents during the code review process.

Does parallel code review assess security and performance aspects?

Parallel code review assesses security and performance aspects using aspect-specific specialized agents. Each agent operates with a fresh context window to provide structured findings complete with severity levels and impact assessments.

Do I need an Agent dependency to run automated PR reviews?

An Agent dependency is required to run automated PR reviews. The parallel multi-agent architecture relies on this foundational component to spawn specialized agents for deep file exploration and aspect-specific analysis.