Scans codebase structure and generates token-lean markdown codemaps for architecture, backend, frontend, data, and dependencies, with diff detection and summary report.
From everything-claude-codenpx claudepluginhub memorialmkua-lab/aiclaude/update-codemapsScans codebase structure and generates token-lean markdown codemaps for architecture, backend, frontend, data, and dependencies, with diff detection and summary report.
/update-codemapsAnalyzes codebase structure via imports/exports/dependencies, generates codemaps for architecture/backend/frontend/data, computes diffs from prior versions, updates with approval if >30% changed, and saves diff report.
/update-codemapsScans project structure, identifies types and entry points, generates token-lean codemaps for architecture, backend, frontend, data, and dependencies in docs/CODEMAPS/, detects diffs, adds metadata, and saves reports.
/update-codemapsScans codebase structure and generates token-lean markdown codemaps for architecture, backend, frontend, data, and dependencies, with diff detection and summary report.
/update-codemapsAnalyzes codebase structure via imports/exports/dependencies, generates codemaps for architecture/backend/frontend/data, computes diffs from prior versions, updates with approval if >30% changed, and saves diff report.
/update-codemapsScans codebase for imports/exports/dependencies using TypeScript/Node.js, generates/updates codemaps for architecture/backend/frontend/data, computes diffs vs prior version, saves report.
Analyze the codebase structure and generate token-lean architecture documentation.
Create or update codemaps in docs/CODEMAPS/ (or .reports/codemaps/):
| File | Contents |
|---|---|
architecture.md | High-level system diagram, service boundaries, data flow |
backend.md | API routes, middleware chain, service → repository mapping |
frontend.md | Page tree, component hierarchy, state management flow |
data.md | Database tables, relationships, migration history |
dependencies.md | External services, third-party integrations, shared libraries |
Each codemap should be token-lean — optimized for AI context consumption:
# Backend Architecture
## Routes
POST /api/users → UserController.create → UserService.create → UserRepo.insert
GET /api/users/:id → UserController.get → UserService.findById → UserRepo.findById
## Key Files
src/services/user.ts (business logic, 120 lines)
src/repos/user.ts (database access, 80 lines)
## Dependencies
- PostgreSQL (primary data store)
- Redis (session cache, rate limiting)
- Stripe (payment processing)
Add a freshness header to each codemap:
<!-- Generated: 2026-02-11 | Files scanned: 142 | Token estimate: ~800 -->
Write a summary to .reports/codemap-diff.txt: