coderabbit или clean-code-assistant

Your code review partner. CodeRabbit provides external validation using a specialized AI architecture and 40+ integrated static analyzers—offering a different perspective that catches bugs, security vulnerabilities, logic errors, and edge cases. Context-aware analysis via AST parsing and codegraph relationships. Automatically incorporates CLAUDE.md and project coding guidelines into reviews. Useful after writing or modifying code, before commits, when implementing complex or security-sensitive logic, or when a second opinion would increase confidence in the changes. Returns specific findings with suggested fixes that can be applied immediately. Free to use.

Enforces clean code principles across your project and fixes the code for you - not just flags what's wrong. Ships with 14 plain-language rules (formal textbook names in parentheses for experts), 13 skills, a background reviewer agent that appends non-blocking suggestions after every edit, and a plan-mode hook that reminds Claude to factor clean code into every plan. Every detection skill supports both report-only mode and a fix mode that applies the changes directly. Multi-platform: generates matching configs for Cursor (.cursorrules) and Codex CLI (AGENTS.md) from one source of truth. Based on Code Complete 2nd Ed., The Art of Clean Code, and OOP vs. Functional Programming.