development-guide

A project-specific development guide for the Rakit UI AI project, which is written in TypeScript and includes a server based on the Model Context Protocol. It describes the project's files, commands, and development process.

In plain words
What is it for?
Use it to edit tools and templates, run the development watcher, start the server, build the project, review planned work, and add tests.
Why use it?
It gives contributors a single reference for how this particular project is structured, built, run, tested, and improved.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/madebyaris/rakitui-ai/development-guide
Clone the repo
git clone --depth 1 https://github.com/madebyaris/rakitui-ai

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00446
Opus 5 $0.00000 $0.00223
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash e241c4c07203, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

development-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/development-guide.mdc · 63 lines

What it actually says

Development Guide

This guide covers the development workflow for the Rakit UI AI project.

Project Setup

  • package.json defines the project dependencies and scripts
  • TypeScript configuration is in tsconfig.json
  • The project uses ES modules (type: "module" in package.json)
  • Check TODO.md for planned improvements and features

Build & Run

  • npm run build: Cleans dist directory, compiles TypeScript, and builds MCP
  • npm run watch: Watches for changes during development
  • npm start: Starts the MCP server from the compiled dist directory

Key Dependencies

  • @modelcontextprotocol/sdk: Core MCP SDK
  • mcp-framework: Framework for building MCP tools
  • open: Library for opening URLs in the default browser

Development Workflow

  1. Create/modify tool implementations in src/tools/
  2. Update templates as needed in src/tools/templates/
  3. Run npm run watch for development
  4. Test using npm start
  5. Build for distribution with npm run build

Working on Improvements

  1. Check TODO.md for prioritized tasks
  2. Create feature branches for each improvement
  3. Follow the security guidelines in security-best-practices rule
  4. Add tests according to testing-strategy rule
  5. Optimize performance following performance-optimization rule

Testing

  • Unit tests: npm test (once implemented)
  • Integration tests: npm run test:integration
  • E2E tests: npm run test:e2e
  • Coverage report: npm run test:coverage

Contributing

  1. Pick a task from TODO.md
  2. Create a feature branch
  3. Implement with tests
  4. Update documentation
  5. Submit pull request

Note on Browser Integration

The server creates temporary files in a tmp directory at the project root. Make sure this directory has appropriate permissions for file creation.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 63 lines · 0 tokens per session scan A e241c4c07203

Subscribe to this mod's changes

development-guide is a cursor rule published in the GitHub repository madebyaris/rakitui-ai (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 446 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.