/Catalogue/Prompt/rohitg00/rohitg00-pro-workflow-module-map

Origin: github

module-map

Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says "I do not know this area", "give me the map", "zoom out", "orient me".

by rohitg00 · updated 1d ago · imported from GitHub

Installs0+0/7d
Security score98/100
Retention 14d0%
GitHub stars2.9K

Skill logic

Execution graph
User message
Prompt rewrites behaviour
Response

SKILL.md

View on GitHub ↗

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.

Discussion

No comments yet — start the thread.

Sign in to join the discussion.

/More from rohitg00/pro-workflow

rohitg00· 1d agoCommunity
skill-optimizer

Prompts · JavaScript · v0.1.0

SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.

#agent-orchestration#ai-agents#ai-coding

0 2.9K
rohitg00· 1d agoCommunity
agent-teams

Prompts · JavaScript · v0.1.0

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.

#agent-orchestration#ai-agents#ai-coding

0 2.9K
rohitg00· 1d agoCommunity
auto-setup

Prompts · JavaScript · v0.1.0

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.

#agent-orchestration#ai-agents#ai-coding

0 2.9K
rohitg00· 1d agoSandbox
batch-orchestration

Prompts · JavaScript · v0.1.0

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.

#agent-orchestration#ai-agents#ai-coding

0 2.9K