project-context.md file to ensure AI agents follow your project’s technical preferences and implementation rules throughout all workflows.
Prerequisites
- BMad Method installed
- Understanding of your project’s technology stack and conventions
When to Use This
- You have strong technical preferences before starting architecture
- You’ve completed architecture and want to capture decisions for implementation
- You’re working on an existing codebase with established patterns
- You notice agents making inconsistent decisions across stories
Step 1: Choose Your Approach
Manual creation — Best when you know exactly what rules you want to document Generate after architecture — Best for capturing decisions made during solutioning Generate for existing projects — Best for discovering patterns in existing codebasesStep 2: Create the File
Option A: Manual Creation
Create the file at_bmad-output/project-context.md:
Option B: Generate After Architecture
Run the workflow in a fresh chat:Option C: Generate for Existing Projects
For existing projects, run:Step 3: Verify Content
Review the generated file and ensure it captures:- Correct technology versions
- Your actual conventions (not generic best practices)
- Rules that prevent common mistakes
- Framework-specific patterns
What You Get
Aproject-context.md file that:
- Ensures all agents follow the same conventions
- Prevents inconsistent decisions across stories
- Captures architecture decisions for implementation
- Serves as a reference for your project’s patterns and rules
Tips
Next Steps
- See which workflows load project context in the workflow documentation
- Customize agents to remember project-specific patterns
