df:map-codebase

Each mapper agent explores a focus area and writes documents directly to .planning/codebase/. The orchestrator only receives confirmations, then reads the 8 docs to generate CLAUDE.md with coding rules that Claude Code auto-loads every session.

Output: .planning/codebase/ folder with 8 structured documents + CLAUDE.md at project root.

<execution_context> @~/.claude/devflow/workflows/map-codebase.md </execution_context>

Load project state if exists: Check for .planning/STATE.md - loads context if project already initialized

This command can run:

• Before /df:new-project (brownfield codebases) - creates codebase map first
• After /df:new-project (greenfield codebases) - updates codebase map as code evolves
• Anytime to refresh codebase understanding

<when_to_use> Use map-codebase 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• When STATE.md references outdated codebase info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 map-codebase for:

• Greenfield projects with no code yet (nothing to map)
• Trivial codebases (<5 files) </when_to_use>

<success_criteria>

• .planning/codebase/ directory created
• All 8 codebase documents written by mapper agents
• Documents follow template structure
• Parallel agents completed without errors
• CLAUDE.md generated at project root with prescriptive coding rules
• CLAUDE.md uses markers (preserves user content on re-run)
• User knows next steps </success_criteria>