codebase-mapping
The codebase-mapping skill automatically catalogs a project's structure, file types, entry points, dependencies, and test patterns to build a comprehensive index. This index is invisibly injected into Claude's context during user interactions, enabling the model to generate code and suggestions that align with the project's conventions and architecture without requiring explicit user description of the codebase. Use it at the start of ClaudeKit sessions or when project structure changes significantly.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/codebase-mapping && cp -r /tmp/codebase-mapping/library/methodologies/claudekit/skills/codebase-mapping ~/.claude/skills/codebase-mappingSKILL.md
- 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)
Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
>-
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.