map-codebase

---

name: map-codebase description: Analyze codebase with parallel Explore agents to produce .planning/codebase/ documents argument-hint: "[optional: specific area to map, e.g., 'api' or 'auth']" allowed-tools:

• Read
• Bash
• Glob
• Grep
• Write
• Task

---

This command spawns multiple Explore agents to analyze different aspects of the codebase in parallel, each with fresh context.

Output: .planning/codebase/ folder with 7 structured documents about the codebase state.

<execution_context> @/.claude/ag4one/workflows/map-codebase.md @/.claude/ag4one/templates/codebase/stack.md @/.claude/ag4one/templates/codebase/architecture.md @/.claude/ag4one/templates/codebase/structure.md @/.claude/ag4one/templates/codebase/conventions.md @/.claude/ag4one/templates/codebase/testing.md @/.claude/ag4one/templates/codebase/integrations.md @/.claude/ag4one/templates/codebase/concerns.md </execution_context>

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

This command can run:

• Before /ag4:new-project (brownfield codebases) - creates codebase map first
• After /ag4: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• When STATE.md references outdated codebase info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 7 codebase documents written
• Documents follow template structure
• Parallel agents completed without errors
• User knows next steps </success_criteria>