Agent Rules Kit v2.0

Bootstrap Cursor rules (.mdc) for AI agent-guided projects. This tool helps you generate and maintain project-specific rules for multiple frameworks and architectures.

What is Agent Rules Kit?

Agent Rules Kit is a CLI tool that facilitates the installation and configuration of rules for Cursor AI, the AI-powered IDE. The rules help AI agents better understand the structure, patterns, and best practices of different technology stacks.

🎧 Audio Introduction

Listen to a brief introduction about Agent Rules Kit:

podcast_en.mp4

English Version

podcast_es.mp4

Spanish Version

📚 Table of Contents

1. Quick Start
2. New Architecture
3. New Features
4. Supported Stacks
5. MCP Tools Integration
6. Implementation Status
7. Contributing
8. Code of Conduct
9. License

🚀 Quick Start

# Install and run interactively
npx agent-rules-kit

# The CLI will guide you through:
# 1. 📁 Project path selection
# 2. 📚 Stack and architecture choice (optional)
# 3. 🌐 Global best practices (recommended)
# 4. 🔧 MCP tools selection (multiple tools supported)
# 5. ⚡ Automatic rule generation

Your rules will be generated in .cursor/rules/rules-kit/ and automatically detected by Cursor!

Available Options

• Stack Selection: Choose the main framework or technology for your project
• Global Rules: Include general best practice rules
• Cursor Directory: Specify the location of the Cursor directory
• Project Path: Define the relative path if the project is not in the root
• Mirror Documentation: Generate .md files that reflect the rules for human reference
• Debug Mode: Enable detailed logging for troubleshooting

🎉 New Architecture

We've completely redesigned the internal architecture to provide a more maintainable and extensible system:

• Service-Based Architecture: Replaced the helper-based system with a clean service-oriented architecture that enhances maintainability and extensibility
• Automatic Backups: Smart backup system that preserves your custom rules when updating
• Enhanced Debug Mode: Better visibility into the rule generation process with standardized logging
• Improved Testing Framework: More robust testing with better mocking and service isolation
• React Architecture Options: Now includes support for atomic design and feature-sliced design
• Better State Management Support: Enhanced support for modern state management libraries

🎉 New Features

• 🚀 Quick setup of rules for different frameworks and stacks
• 🔍 Automatic framework version detection
• 🏗️ Support for multiple architectural styles
• 📚 Mirror documentation generation for human reference
• 🧩 Modular system for easy expansion to new frameworks
• 💾 Automatic backups of existing rules
• 🔄 Version-specific rule overlays
• 🔧 Multi-select MCP Tools integration (New in v2.0)

🔧 MCP Tools Integration

New in v2.0: Agent Rules Kit now includes comprehensive support for Model Context Protocol (MCP) tools! This powerful feature allows AI agents to work more effectively with external tools and services.

What are MCP Tools?

Model Context Protocol (MCP) tools are standardized interfaces that allow AI assistants to securely connect to external data sources and services. These tools enable AI agents to:

• 🔍 Search codebases semantically with understanding of code meaning
• 🐙 Manage repositories with secure GitHub integration
• 🧠 Maintain persistent memory across conversation sessions
• 📁 Access file systems with configurable security controls
• 🔀 Perform version control operations with Git integration

Available MCP Tools

Choose from 5 popular MCP tools during installation:

Tool	Name	Description	Best For
🔍 PAMPA	Semantic Code Search	AI-powered code search with project memory	Understanding large codebases, finding relevant code patterns
🐙 GitHub	Repository Management	Secure GitHub API integration for file operations	Repository management, collaborative development
🧠 Memory	Persistent Knowledge	Long-term memory storage across sessions	Maintaining context, learning from previous interactions
📁 Filesystem	File Operations	Secure file system access with controls	File management, project organization
🔀 Git	Version Control	Repository operations and history analysis	Version control, commit management, branch operations

Multi-Select Installation

The new multi-select interface allows you to install rules for multiple MCP tools simultaneously:

? Select MCP tools to install rules for: (Use space to select, enter to confirm)
❯◉ PAMPA - Semantic Code Search - AI-powered semantic code search and project memory system
 ◉ GitHub - Repository Management - Secure access to GitHub repositories for file operations
 ◯ Memory - Persistent Knowledge - Persistent knowledge storage and retrieval across sessions
 ◉ Filesystem - File Operations - Secure file operations with configurable access controls
 ◯ Git - Version Control - Repository operations, commit history analysis, and version control

Generated Rule Structure

Each selected MCP tool generates organized rules in your project:

.cursor/rules/rules-kit/mcp-tools/
├── pampa/
│   ├── pampa-mcp-usage.mdc       # Core usage patterns
│   └── pampa-best-practices.mdc  # Best practices and tips
├── github/
│   ├── github-mcp-usage.mdc      # GitHub API integration rules
│   └── github-workflow.mdc       # Workflow patterns
└── memory/
    ├── memory-mcp-usage.mdc      # Memory management rules
    └── memory-patterns.mdc       # Common memory patterns

Benefits for AI Agents

MCP Tools rules help AI agents:

1. 🎯 Use tools effectively: Clear guidelines on when and how to use each tool
2. 🛡️ Follow security best practices: Built-in security patterns and access controls
3. ⚡ Optimize performance: Efficient usage patterns to avoid rate limits and errors
4. 🔄 Handle errors gracefully: Common error scenarios and recovery strategies
5. 📖 Learn workflows: Step-by-step patterns for complex operations

Integration with Stack Rules

MCP tools rules work alongside your stack-specific rules:

• 🔀 Independent Generation: MCP rules are separate from stack rules
• 🧩 Flexible Combinations: Any stack + any combination of MCP tools
• 🎯 Focused Guidance: Tool-specific rules don't interfere with framework patterns
• 📋 Complete Coverage: Both development patterns AND tool usage covered

Supported Stacks

• Laravel (v8-12)
• Next.js (v12-14)
• React (v17-18)
• React Native
• Angular (v14-17)
• NestJS
• Vue (v2-3)
• Nuxt (v2-3)
• Svelte (v3-5)
• SvelteKit (v1-2)
• Astro
• Generic (for any project)

Implementation Status

Stack	Status	Features
		NEW v2.0: Multi-select MCP tools (PAMPA, GitHub, Memory, Filesystem, Git), usage patterns, security guidelines, workflows
		Complete SDK coverage (Python, TypeScript, Java, Kotlin, C#, Swift), server/client patterns, architecture concepts
		Multiple architectures, version detection, casting rules
		Testing guidelines, architectural patterns, version-specific docs
		Best practices, file operations, code standards, extensibility docs
		Semantic code search, AI agent integration, MCP support, multi-language indexing
		Architecture options, state management, testing guidelines, version-specific guidance (v18 concurrent features)
		Base rules (architecture, best practices, styling, naming, navigation, platform code, state, testing, version info)
		App & Pages router support, version detection, testing docs, version-specific guidance (v13 API routes, v14 Server Components)
		Component organization, runes (v5), lifecycle, state management
		Multiple architectures, project structure, error handling patterns
		Routing system, layouts, SSR/CSR strategies, form actions
		Content collections, static/dynamic content, integration guides
		Signals support, base project structure
		Standard and Microservices architectures, NestJS 9.x and 10.x features
		Testing guidelines, architecture concepts
		Standard, Reactive, Microservices

Enhanced Extensibility: Detailed documentation has been added on how to extend Agent Rules Kit with new services, making it easier to contribute new stacks and features.

Contributing

For guidelines on contributing to this project, please see CONTRIBUTING.md.

Code of Conduct

Please read our Code of Conduct before participating in our project.

License

This project is licensed under the ISC License. See the LICENSE file for details.

🎯 Available Stacks

Choose from a wide range of technology stacks:

Stack	SDKs/Versions	Architectures
Laravel	8, 9, 10, 11	Standard, DDD, Hexagonal
Next.js	12, 13, 14, 15	App Router, Pages Router
Angular	12, 13, 14, 15, 16, 17, 18	Standard, Standalone, Micro-frontends
React	16, 17, 18, 19	Standard, Hooks, Concurrent
Vue.js	2, 3	Options API, Composition API, Nuxt
Astro	3, 4	Static, SSR, Hybrid
React Native	0.70, 0.71, 0.72, 0.73, 0.74	Standard, Expo
NestJS	8, 9, 10	Standard, Microservices, GraphQL
Go	1.20, 1.21, 1.22	Standard, DDD, Hexagonal
Django	4, 5	MVT, API, Full-Stack
FastAPI	0.100+	Standard, Async, Microservices
Express.js	4	Standard, REST, GraphQL
Spring Boot	2, 3	Standard, Reactive, Microservices
🆕 MCP (Model Context Protocol)	Python, TypeScript, Java, Kotlin, C#, Swift	Server, Client, Toolkit
🆕 Pampa	Latest	Standard

🔥 Featured: Model Context Protocol (MCP) SDKs

MCP is an open standard that enables AI applications to securely connect to data sources. Our rules kit includes comprehensive implementation guides for all major SDKs:

• 📖 Architecture Concepts: Core MCP patterns and best practices
• 🐍 Python SDK: Async/await patterns with Pydantic validation
• 🟦 TypeScript SDK: Type-safe implementations with modern JS patterns
• ☕ Java SDK: Enterprise patterns with Spring Boot integration
• 🎯 Kotlin SDK: Coroutines and advanced async features
• 🔷 C# SDK: .NET patterns with dependency injection
• 🍎 Swift SDK: Actors and async/await with Vapor integration

🎯 Featured: Pampa Semantic Code Search

Pampa is our own AI-powered semantic code search tool designed specifically for AI agents:

• 🔍 Semantic Search: Understand code meaning, not just syntax
• 🤖 AI Agent Optimized: Built specifically for AI agent workflows
• 🌍 Multi-Language: Python, TypeScript, Java, Go, PHP, and more
• 🚀 Simple Setup: No versions, no complex config - just install and use
• 🔌 MCP Integration: Built-in MCP server for seamless AI integration

Perfect for AI agents to quickly understand and navigate any codebase!

✨ Key Features

• 🎯 Multi-Stack Support: 15+ frameworks including Laravel, Next.js, React, Angular, Vue, and more
• 🏗️ Architecture-Aware: Specialized rules for different architectural patterns (MVC, DDD, Hexagonal, etc.)
• 📦 Version Detection: Automatic framework version detection with version-specific optimizations
• 🌐 Global Best Practices: Universal coding standards and quality assurance rules
• 🔧 MCP Tools Integration: Multi-select support for popular Model Context Protocol tools (PAMPA, GitHub, Memory, Filesystem, Git)
• ⚡ Performance Optimized: Efficient rule generation with progress tracking and memory management
• 🔄 Smart Updates: Backup existing rules and merge configurations intelligently
• 🎨 Beautiful CLI: Interactive interface with helpful prompts and clear feedback