agentleFS
Sapere-IASapere-IA/sdd-onboarding-kit/skills/optional/project-map/SKILL.md

project-map

Skill19 starsChanged 37 days agoMITView on GitHub

Generate or refresh the project map artifact. Use after significant repository structure changes or when the map is missing or stale.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    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. Very specific:

    Create or update the project map — the concise orientation artifact (default <harness-dir>/context/project-map.md) that tells the agent …

    line 10
  2. Distinctive:

    Keep it one to two screens.

    line 41
  3. Distinctive:

    Verify AGENTS.md links the map at its configured location.

    line 43
  4. Distinctive:

    Never record secrets, credentials, or tokens.

    line 52
  5. Distinctive:

    Do not change AGENTS.md beyond the map link without approval.

    line 53
  6. Distinctive:

    If the map's configured location is unclear, ask instead of creating a second map.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Project map

Purpose

Create or update the project map — the concise orientation artifact (default <harness-dir>/context/project-map.md) that tells the agent where things live without loading many files. See DOCUMENTATION.html §16 in the kit.

When to use

  • The map does not exist (generation was deferred at onboarding).
  • A top-level or load-bearing directory was added, renamed, or removed.
  • An entrypoint moved, or build/test/lint commands changed.
  • A new protected area or generated path appeared.
  • The map demonstrably disagrees with the repository.

When not to use

  • Routine file additions inside existing directories.
  • As a substitute for reading actual code when implementing.

Required inputs

  • The map template (templates/project-map.md.template in the kit, or the existing generated map).
  • Repository inspection: directory tree (depth 2–3), package manifests, scripts, CI config, docs.
  • The project AGENTS.md protected-areas section.

Procedure

  1. Inspect the repository (prefer a subagent if the survey is large).
  2. Fill or update the map's eight sections: tree, entrypoints, commands, framework/runtime assumptions, important docs, protected areas, SDD locations, generated/do-not-edit files.
  3. Keep it one to two screens; annotate, do not enumerate.
  4. Record unknown commands as TODO: ask the developer — never invent.
  5. Verify AGENTS.md links the map at its configured location.

Output artifact

The project map file at its configured location (default <harness-dir>/context/project-map.md).

Safety constraints

  • Never record secrets, credentials, or tokens.
  • Do not change AGENTS.md beyond the map link without approval.
  • If the map's configured location is unclear, ask instead of creating a second map.

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.