millionco/react-doctor

Your agent writes bad React. This catches it

What it solves

React Doctor addresses the issue of poor quality React code, specifically when generated by AI coding agents. It provides a deterministic scan of a codebase to identify issues related to state and effects, performance, architecture, security, and accessibility.

How it works

It operates as a CLI tool that scans the project root to perform an audit. It can be integrated into CI/CD pipelines (such as GitHub Actions) to review pull requests and report only new issues introduced by changes. Additionally, it offers a "skill" that can be installed for coding agents (like Claude Code, Cursor, and Codex) to help them learn from identified issues and avoid repeating mistakes.

Who it’s for

Developers and teams using React-based frameworks (Next.js, Vite, Astro, TanStack, React Native, Expo) who want to ensure code quality and reduce the bugs introduced by AI agents.

Highlights

  • Deterministic scanning for state, effects, performance, security, and accessibility.
  • Integration with AI coding agents to improve their output quality.
  • CI/CD support to prevent new regressions in pull requests.
  • Compatible with a wide range of React frameworks and environments.

Related

  • Project
    TheOrcDev/shadscan

    A deterministic UI audit tool for shadcn/ui React apps that scores UI fundamentals and provides actionable remediation plans for developers and AI agents.

  • Project
    alibaba/open-code-review

    An AI-powered code review CLI tool that combines deterministic engineering with an agentic workflow to provide high-precision, line-level feedback on Git diffs and full files.

  • Project
    suleimanodetoro/skills

    A collection of specialized agent skills for designing, building, and reviewing software in React, React Native, and security.

  • Project
    reticlehq/reticle

    A verification layer for AI coding agents that runs an internal SDK in web apps to prove code changes work by monitoring network, state, and console events.

  • Project
    TheAuditorTool/Auditor

    A local, database-first code intelligence and SAST platform that turns codebases into queryable facts to reduce token costs for AI agents and security teams.