Skip to content
🤖 Consolidated, AI-optimized BMAD docs: llms-full.txt. Fetch this plain text file for complete context.

Manage Project Context

Use the project-context.md file to ensure AI agents follow your project’s technical preferences and implementation rules throughout all workflows.

  • 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

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 codebases

Create the file at _bmad-output/project-context.md:

Terminal window
mkdir -p _bmad-output
touch _bmad-output/project-context.md

Add your technology stack and implementation rules:

---
project_name: 'MyProject'
user_name: 'YourName'
date: '2026-02-15'
sections_completed: ['technology_stack', 'critical_rules']
---
# Project Context for AI Agents
## Technology Stack & Versions
- Node.js 20.x, TypeScript 5.3, React 18.2
- State: Zustand
- Testing: Vitest, Playwright
- Styling: Tailwind CSS
## Critical Implementation Rules
**TypeScript:**
- Strict mode enabled, no `any` types
- Use `interface` for public APIs, `type` for unions
**Code Organization:**
- Components in `/src/components/` with co-located tests
- API calls use `apiClient` singleton — never fetch directly
**Testing:**
- Unit tests focus on business logic
- Integration tests use MSW for API mocking

Run the workflow in a fresh chat:

Terminal window
/bmad-bmm-generate-project-context

The workflow scans your architecture document and project files to generate a context file capturing the decisions made.

For existing projects, run:

Terminal window
/bmad-bmm-generate-project-context

The workflow analyzes your codebase to identify conventions, then generates a context file you can review and refine.

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

Edit manually to add anything missing or remove inaccuracies.

A project-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