🎯 AI Context Rules System

🌟 Quick Overview

A comprehensive system for managing AI interactions through memory management, lessons learned tracking, and dual-mode operation (Plan/Agent). This system ensures consistent, high-quality development while maintaining detailed project documentation and knowledge retention.

🔄 Core Components

1. Memory System (@memories.md)

   • Tracks all interactions chronologically
   • Auto-updates with timestamps and tags
   • Maintains project context and decisions
   • Uses version control format [v1.0.0]
   • Supports #tags for easy searching

2. Lessons Learned (@lessons-learned.md)

   • Captures solutions and best practices
   • Uses structured format: Issue → Solution → Impact
   • Categorizes by component, TypeScript, errors, etc.
   • Prioritizes issues (Critical/Important/Enhancement)
   • Links to related code examples

3. Scratchpad (@scratchpad.md)

   • Manages current phase and tasks
   • Tracks implementation progress
   • Uses clear status markers [X], [-], [ ], [!], [?]
   • Maintains task dependencies
   • Updates confidence metrics

🎯 Mode System Operation

Plan Mode 🎯

Trigger: "plan"
Purpose: Information gathering and planning
Requirements:
- Parse user input
- Cross-reference requirements
- Generate clarifying questions
- Calculate confidence score
- Create task breakdown

Agent Mode ⚡

Trigger: "agent"
Activation Requirements:
- 95% confidence level
- All questions answered
- Tasks defined
- No blocking issues
- Requirements verified

🚀 Workflow Steps

1. Initialize Planning 🎯

   hljs language-markdown

   Copy

   - Use "plan" trigger
   - System creates new scratchpad entry
   - Generates minimum 3 questions
   - Sets initial confidence score
   

2. Build Confidence 📈

   hljs language-markdown

   Copy

   - Answer all questions
   - Verify requirements
   - Update task dependencies
   - Monitor confidence score
   

3. Execute Implementation ⚡

   hljs language-markdown

   Copy

   - Reach 95% confidence
   - Use "agent" trigger
   - System implements solution
   - Updates documentation
   

🎮 Workflow Examples

Example 1: Creating a New Feature

USER: "plan implement a new button component"

AI: 🎯 PLAN MODE ACTIVATED
Current Task: Implement new button component
Questions:
1. What variants are needed? (primary/secondary/outline)
2. Should it support icons?
3. What sizes are required?
Confidence: 65%

USER: "primary and secondary variants, with icons, three sizes"

AI: Updated Understanding:
- Primary/Secondary variants
- Icon support
- Small/Medium/Large sizes
Confidence: 95%

USER: "agent"

AI: ⚡ AGENT MODE ACTIVATED
- Creating Button component
- Implementing variants
- Adding icon support
- Testing accessibility

Example 2: Fixing a Bug

USER: "plan fix the form submission error"

AI: 🎯 PLAN MODE ACTIVATED
Current Task: Debug form submission error
Questions:
1. When does the error occur?
2. Any error messages in console?
3. Which form component is affected?
Confidence: 50%

USER: "happens on login form, console shows validation error"

AI: Chain of Thought Analysis:
1. Login form validation
2. Console error check
3. Input validation rules
Confidence: 95%

USER: "agent"

AI: ⚡ AGENT MODE ACTIVATED
- Debugging validation
- Fixing error handling
- Testing submission

Example 3: Project Setup

USER: "plan setup new Next.js project"

AI: 🎯 PLAN MODE ACTIVATED
Current Task: Initialize Next.js project
Questions:
1. Which version of Next.js?
2. TypeScript or JavaScript?
3. Which UI components needed?
Confidence: 70%

USER: "Next.js 14, TypeScript, Shadcn UI"

AI: Project Structure:
- Next.js 14 setup
- TypeScript configuration
- Shadcn UI integration
Confidence: 95%

USER: "agent"

AI: ⚡ AGENT MODE ACTIVATED
- Creating project
- Setting up TypeScript
- Installing dependencies

Example 4: Documentation Update

USER: "plan update API documentation"

AI: 🎯 PLAN MODE ACTIVATED
Current Task: Update API docs
Questions:
1. Which endpoints need updates?
2. Any new parameters added?
3. Response format changes?
Confidence: 60%

USER: "new authentication endpoints"

AI: Documentation Plan:
- Auth endpoints
- Request/Response formats
- Example usage
Confidence: 95%

USER: "agent"

AI: ⚡ AGENT MODE ACTIVATED
- Updating docs
- Adding examples
- Verifying formats

📝 Documentation Standards

Real-time Updates

• Memories: Every interaction
• Lessons: After solutions
• Scratchpad: During implementation

Version Control

[v1.0.0] Format for all entries
- Development updates
- Manual updates
- Progress tracking

Cross-referencing

@memories.md ↔️ @lessons-learned.md ↔️ @scratchpad.md

🔍 Directory Structure

.cursor/
├── memories.md          # Interaction history
├── lessons-learned.md   # Solutions & practices
├── scratchpad.md       # Current phase tracking
├── project-requirements.md  # Project specs
└── rules/              # System rules
    └── .cursorrules    # Core rules file

🛠️ Best Practices

1. Memory Management

   • Use timestamps consistently
   • Include relevant #tags
   • Cross-reference related entries
   • Keep single-line format

2. Task Tracking

   • Generate unique task IDs
   • Track dependencies
   • Update status in real-time
   • Maintain hierarchy

3. Documentation

   • Update in real-time
   • Include version numbers
   • Cross-reference related files
   • Follow structured formats

🎯 Tips & Tricks

🔄 Handling AI & Cursor Issues

1. Required Open Tabs:

   hljs language-scss

   Copy

   1️⃣ Active working file
   2️⃣ Cursor Settings (Feature → Resync)
   3️⃣ .cursorrules (for auto-reload)
   

2. Quick Reload Process:

   hljs language-markdown

   Copy

   1. Ctrl+Shift+P
   2. "Developer: Reload Window"
   3. Wait 3-10 seconds
   

💡 Pro Tips

• Keep .cursorrules file open
• Monitor confidence scores
• Use proper triggers
• Follow version format
• Cross-reference frequently

🤝 Contributing

Feel free to enhance this system:

1. Add custom rules
2. Improve tracking
3. Enhance metrics
4. Share practices

📝 License

MIT License - Free to use and modify!

👋 Contacts / Hire me

• Instagram: https://www.instagram.com/clover_nat/
• Facebook: https://www.facebook.com/nathanielmarquez.20
• Twitter: https://x.com/T1nker1220

💖 Support This Project

If this system helps you, consider supporting:

• PayPal: https://www.paypal.me/JohnNathanielMarquez
• GCash: 09605088715

📚 Learn More

For full context and discussions: https://forum.cursor.com/t/rules-for-ultra-context-memories-lessons-scratchpad-with-plan-and-act-modes/48792/22?u=t1nker-1220

Note: This system is designed for seamless AI interaction management. For detailed implementation guidelines, refer to the individual rule files. 🚀