10 boosters for "code-review" — AI-graded, open source, ready to install
Heuristic scoring (no AI key configured).
Actionable refactoring suggestions for improving clean architecture compliance in Rust projects
A multi-agent framework that dynamically spawns specialized agents (frontend, backend, DevOps, etc.) to autonomously handle software development tasks across platforms like Claude and OpenAI. Developers building complex applications benefit from delegating work to a coordinated swarm of AI agents that each handle domain-specific responsibilities.
An AI-powered code review agent that automatically analyzes code changes for quality, security, and maintainability issues, providing prioritized feedback with specific fixes. Ideal for developers seeking proactive code quality assurance and security vetting in their workflows.
A code review skill that validates pull requests across multiple languages (Python, JavaScript, TypeScript, React) against acceptance criteria, checking correctness, security, maintainability, and test coverage. Developers and code reviewers use this to ensure quality and consistency before merging.
A governance skill that automates code review and standards enforcement through delegated agent execution, delivering 70-90% token savings for engineering teams managing code quality at scale.
Hack Review is a system prompt that transforms Claude into an expert code reviewer for pull requests, providing automated feedback on bugs, style, performance, and security issues. It benefits developers and teams who want AI-assisted code review integrated into their GitHub workflow.
code-reviewer-pro is an AI-powered senior engineering lead that provides comprehensive code reviews covering quality, security, maintainability, and best practices with actionable feedback. Developers benefit from immediate, educational code analysis after writing or modifying code.
Apply targeted fixes from critics/mutation within subtask scope → .runs/<run-id>/build/fix_summary.md (countable markers).
