Run a complete project analysis in one call. Returns git history stats, project structure with file counts, curated code sample previews (~60 lines each), and test-to-source file mapping. This is the recommended starting point — call this first, then read specific files natively for full content.

Run git history analysis on a codebase. Returns commit convention patterns, stale directories, and frequently changed files. These are aggregate stats across hundreds of commits that would be expensive to compute manually.

Get previews (first ~60 lines) of representative source files from the codebase. Includes entry points, config files, hot files (frequently changed), test examples, and one file per directory for breadth. Read files natively for full content.

Get the project's concept map — a lookup table from features and flows to the files that implement them. Use this to jump straight to relevant files instead of exploring. Example: 'home screen' → [HomeScreen.kt, HomeViewModel.kt, HomeModule.kt]. If stale, run 'mason snapshot-update' to refresh.

Save a concept-to-files map as a persistent project snapshot. Maps feature names and data flows to the files that implement them. Persists across conversations — future sessions can call get_snapshot to instantly find relevant files. No API key needed — you are the LLM generating the map.

Analyze the impact of changing specific files. Returns three signals: git co-change (files that historically change together), references (files that mention the target by name), and related tests. Use this before editing a file to understand what else might need updating.