agentleFS
Sign inStart free
wedabrowedabro/bro-skills/.agents/skills/speckit.map/SKILL.md

speckit.map

Skill3 starsChanged 45 days agoMITView on GitHub

Codebase Mapper - Build a bounded, evidence-backed architecture and dependency map for existing projects.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a navigable map of structure, ownership, dependencies, conventions, integrations, and runtime boundaries without loading the whole …

    line 7
  2. Distinctive:

    Read project config, manifests, entrypoints, exports, Docker files, and representative source slices.

    line 10
  3. Very specific:

    Write .agents/codebase/ARCHITECTURE.md, STRUCTURE.md, INTEGRATIONS.md, and CONVENTIONS.md with scan scope and timestamp.

    line 11
  4. Distinctive:

    Update maps after major refactors and compare the previous map to surface structural drift.

    line 18
  5. Distinctive:

    Every output states scope, date, evidence, unknowns, and confidence.

    line 21
  6. Distinctive:

    Read-only. Do not scan secrets into reports, read every file indiscriminately, or invent dependencies from naming alone.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mission

Create a navigable map of structure, ownership, dependencies, conventions, integrations, and runtime boundaries without loading the whole repository into context.

Inputs and Outputs

  • Read project config, manifests, entrypoints, exports, Docker files, and representative source slices.
  • Write .agents/codebase/ARCHITECTURE.md, STRUCTURE.md, INTEGRATIONS.md, and CONVENTIONS.md with scan scope and timestamp.

Protocol

  1. Identify repository type, languages, frameworks, package managers, services, build/test commands, and generated/vendor paths.
  2. Enumerate directories and entrypoints; sample headers/exports before reading implementation details. Use CodeGraph when .codegraph/ exists; otherwise use rg.
  3. Trace imports, routes, jobs, data stores, external services, configuration, and critical request/event paths. Distinguish confirmed links from inferred ones.
  4. Record ownership boundaries, shared utilities, duplication, cycles, risk hotspots, and unknowns with file:line evidence.
  5. Update maps after major refactors and compare the previous map to surface structural drift.

Completion Gate

Every output states scope, date, evidence, unknowns, and confidence; major runtime and integration boundaries are traceable to source locations.

Guard Rails

Read-only. Do not scan secrets into reports, read every file indiscriminately, or invent dependencies from naming alone.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free