codebase-mapping
npx machina-cli add skill a5c-ai/babysitter/codebase-mapping --openclawCodebase Mapping
Overview
Auto-indexes the project structure to build a comprehensive codebase map. This map is used for invisible context injection via the UserPromptSubmit hook, providing Claude with project awareness without explicit user prompting.
Map Contents
Project Structure
- Directory tree with depth-limited enumeration
- Key file identification (entry points, configs, lock files)
File Type Distribution
- Language breakdown (TypeScript, JavaScript, Python, etc.)
- Framework detection (React, Next.js, Express, etc.)
Entry Points
- Main entry files (index, main, app)
- CLI entry points
- API route definitions
Module Dependencies
- Import graph analysis
- Package boundary mapping
- Circular dependency detection
Test Layout
- Test directory structure
- Test file patterns and conventions
- Test framework identification
Context Injection
The codebase map is injected as invisible context during UserPromptSubmit, providing:
- Project type and framework awareness
- Convention awareness for code generation
- Dependency awareness for import suggestions
- Test pattern awareness for test generation
When to Use
- Automatically at ClaudeKit session start
- When project structure changes significantly
- Before research or specification tasks
Processes Used By
claudekit-orchestrator(session initialization)claudekit-research(context for research agents)claudekit-spec-workflow(context for spec creation)
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/claudekit/skills/codebase-mapping/SKILL.mdView on GitHub Overview
Codebase mapping automatically catalogs project structure, file types, entry points, dependencies, and test layout to create a comprehensive map. This map is injected as invisible context during UserPromptSubmit to provide Claude with project awareness without explicit prompts.
How This Skill Works
The mapper traverses the repository with a depth-limited directory tree, identifies entry points (index, main, app), configs, and lock files, and builds a dependency graph by analyzing imports and package boundaries. It also detects framework indicators and test layouts to capture framework and test conventions.
When to Use It
- Automatically at ClaudeKit session start
- When the project structure changes significantly
- Before research or specification tasks
- During onboarding of a new repository
- Before code generation or test scaffolding tasks
Quick Start
- Step 1: Enable codebase-mapping in your ClaudeKit session
- Step 2: Run the claudekit mapper to crawl the repository and build the map
- Step 3: Use the generated map as invisible context during UserPromptSubmit
Best Practices
- Run the mapper at repo onboarding to establish a baseline
- Update the map on CI or PRs to reflect changes
- Verify detection of entry points and API routes
- Validate the dependency graph and circular dependencies
- Document test layout conventions exposed by the map
Example Use Cases
- A Next.js + Express monorepo with multiple packages
- A Python Django project with several apps and tests
- A TypeScript library with shared code across packages
- An API-first repo with REST and GraphQL routes
- A large monorepo with lockfiles, multiple frameworks, and CLI tools
