Each mapper agent explores a focus area and writes documents directly to .planning/codebase/. The orchestrator only receives confirmations, keeping context usage minimal.
Output: .planning/codebase/ folder with 7 structured documents, plus .planning/intel/ with compressed agent-readable artifacts (doc-derived summary + code-scanned index and conventions).
<execution_context> @./references/project-analyze.md </execution_context>
Load project state if exists: Check for .planning/STATE.md - loads context if project already initialized
This command can run:
- Before /kata-new-project (brownfield codebases) - creates codebase map first
- After /kata-new-project (greenfield codebases) - updates codebase map as code evolves
- Anytime to refresh codebase understanding
<when_to_use> Use project-analyze for:
- Brownfield projects before initialization (understand existing code first)
- Refreshing codebase map after significant changes
- Onboarding to an unfamiliar codebase
- Before major refactoring (understand current state)
- When STATE.md references outdated codebase info
Skip project-analyze for:
- Greenfield projects with no code yet (nothing to map)
- Trivial codebases (<5 files) </when_to_use>
<success_criteria>
- .planning/codebase/ directory created
- .planning/intel/ directory created with summary.md, index.json, conventions.json
- All 7 codebase documents written by mapper agents
- Documents follow template structure
- Parallel agents completed without errors
- User knows next steps </success_criteria>