agentleFS
KaryawanSurgaKaryawanSurga/tokensaver-plugin/skills/repo-map/SKILL.md

repo-map

Skill1 starsChanged 45 days agoMITView on GitHub

Understand a repository's structure without reading files. Use when orienting in an unfamiliar codebase, finding where a symbol is defined, outlining a single file, or locating entry points before editing.

13 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

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call repo_map with the repository root before opening any file.

    line 28
  2. Very specific:

    Use find_symbol to jump straight to a definition instead of grepping.

    line 30
  3. Very specific:

    Use file_outline before reading a large file.

    line 31
  4. Distinctive:

    When the budget truncates, narrow the path or raise the budget.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 12 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

Repository map

Get the shape of a repository — tree, languages, entry points, and key symbols — in one budgeted call instead of reading dozens of files.

MCP tools

ToolUse it for
repo_mapFirst look: tree, language stats, entry points, exported symbols.
find_symbolWhere is X defined? Returns file, line, kind, visibility.
file_outlineThe shape of one file with line ranges (methods included).
entry_pointsHow does this project start executing?

Workflow

  1. Call repo_map with the repository root before opening any file.
  2. Pick the files that matter from the map.
  3. Use find_symbol to jump straight to a definition instead of grepping.
  4. Use file_outline before reading a large file.
  5. When the budget truncates, narrow the path or raise the budget.

CLI fallback

npx -y tokensaver-mcp            # same tools over MCP

Tips

  • Entry points usually appear in package.json (bin, main, exports) and the tree marks them with *.
  • The map respects .gitignore (including nested files) and skips dependencies automatically.

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.