Usage: /code-review (optional -r or --reset to start a new review, deleting the old review. Otherwise, continue from last run based on the checklist, or start a new review if no checklist exists, if -r is not passed but the checklist exists not complete, then exit with an error).
You are tasked with ensuring .cursor/rules files match and properly expand upon the rules in ./CLAUDE.md. This is a one-way synchronization where CLAUDE.md is the source of truth. Follow these specific instructions.
Generate a complete PLAN for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable self-validation and iterative refinement. Read the feature file first to understand what needs to be created, how the examples provided help, and any other considerations.
Cursor rule "development-workflow" from kurisu-dotto-komu/next-agentic-coding, covering development workflow standards, development server, git operations, documentation creation and testing and linting commands.
Cursor rule "react-components" from kurisu-dotto-komu/next-agentic-coding, covering react component patterns, component export pattern, examples, ❌ bad: named export and ❌ bad: arrow function with default export.
Cursor rule "typescript-patterns" from kurisu-dotto-komu/next-agentic-coding, covering typescript patterns and standards, type system usage, type system integrity, examples and ❌ bad: using any type.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.