module-map
module-map is a Claude Code skill that generates a single-screen architectural overview of unfamiliar code areas, showing entry points, core modules, data flow, external callers, and hidden coupling. Use it when you need rapid orientation in an unfamiliar codebase section and want a factual, file-backed map designed for fifteen-second comprehension rather than a detailed tour.
git clone --depth 1 https://github.com/rohitg00/pro-workflow /tmp/module-map && cp -r /tmp/module-map/skills/module-map ~/.claude/skills/module-mapSKILL.md
# module-map Orient fast in unfamiliar code. The deliverable is a map, not a tour. ## Deliverable A single response containing, in this order: 1. **One-line summary** of what the area does from a caller's point of view. 2. **Entry points** — every function, route, CLI command, event handler, or cron that starts a call chain in this area. File path + symbol. 3. **Core modules** — the two to five modules that contain the real logic. One line each describing their role. 4. **Data flow** — ASCII arrows showing the dominant path for the most common input. Skip error paths unless they matter architecturally. 5. **External callers** — who outside this area calls in, and through which entry points. 6. **Hidden coupling** — anything that looks independent but is not (shared singletons, global state, implicit ordering, undocumented contracts between files). ## Rules - Fifteen-second read target. If the map exceeds one screen, cut it. - Every claim must be backed by a file path. No remembered or inferred structure without a grep behind it. - Do not list every file. Curate. A good map omits deliberately. - Do not propose changes. Mapping is orientation; refactoring is a different skill. - If the area is too large to map in one screen, segment it and ask the user which segment to expand. Do not silently drop half the code. ## Format ``` AREA: <one-line summary> ENTRY POINTS - <path>:<symbol> — <role> CORE MODULES - <path> — <role> FLOW <entry> -> <module> -> <module> -> <sink> CALLERS - <path> — uses <entry> HIDDEN COUPLING - <description> (<path>) ``` Use the exact headers. Consistency lets the user scan.
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.