AGENTS.md

AGENTS.md

Language & Communication

• All documentation, code, comments, and interaction must be in English
• Even if user communicates in Spanish, respond in English

Project Structure

Credentials

• Store all secrets in .env at project root
• Never commit credentials - .env must be in .gitignore

Knowledge Base

• Project-specific discoveries go in doc/resources.md
• Update it when you learn something new about the codebase or dependencies

Workflow Orchestration

1. Plan Mode Default

• Enter plan mode for ANY non-trivial task or architectural decision
• Write plan to tasks/todo.md with checkable items
• If something goes sideways, STOP and re-plan - don't keep pushing
• Check in with user before starting implementation

2. Subagent Strategy

• Use subagents liberally to keep main context window clean
• Offload research, exploration, and parallel analysis
• One coherent scope per subagent for focused execution
• For complex problems, throw more compute at it

3. Self-Improvement Loop

• After ANY correction from user: update tasks/lessons.md with the pattern
• Write rules that prevent the same mistake recurring
• Review lessons at session start

4. Verification Before Done

• Never mark a task complete without proving it works
• Run tests, check logs, demonstrate correctness
• Verify no Pylance/linter errors before finishing
• Diff behavior between main and your changes when relevant

5. Demand Elegance (Balanced)

• For non-trivial changes: pause and ask "is there a more elegant way?"
• If a fix feels hacky, implement the proper solution
• Skip this for simple, obvious fixes - don't over-engineer

6. Autonomous Bug Fixing

• When given a bug report: just fix it. Don't ask for hand-holding
• Point at logs, errors, failing tests - then resolve them
• Fix failing CI tests without being told how

Testing

• Modify test scripts whenever you change functionality
• Never consider a task done without running tests
• Zero tolerance for skipped verification

Task Management

1. Plan First: Write plan to tasks/todo.md with checkable items
2. Verify Plan: Check in before starting implementation
3. Track Progress: Mark items complete as you go
4. Explain Changes: High-level summary at each step
5. Document Results: Add review section to tasks/todo.md
6. Capture Lessons: Update tasks/lessons.md after corrections

Core Principles

• Simplicity First: Make every change as simple as possible
• No Laziness: Find root causes. No temporary fixes. Senior developer standards.
• Minimal Impact: Changes should only touch what's necessary
• Prove It Works: Verification is mandatory, not optional