Skip to content
Agentmart
Submit a tool

codemap

Build or refresh a concise repository map when a codebase's modules, entry points, and dependency boundaries must be understood.

Skill by Rafcin

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rafcin-codemap

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Build or refresh a concise repository map when a codebase's modules, entry points, and dependency boundaries must be understood.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/codemap

What's inside

Skill name
codemap
Description
Build or refresh a concise repository map when a codebase's modules, entry points, and dependency boundaries must be understood.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • clone-dependency.md · references/

SKILL.md (first lines)

# Codemap

## Entry conditions

Use when modules, entry points, or dependency boundaries must be understood. Produce a factual compact map without source edits unless asked to save it. Start with instructions and top-level manifests; use `rg --files` and `rg` to trace entry points, imports, commands, configuration, tests, and generated boundaries.

## Scope limit

Follow only paths needed for the question. Distinguish authored source, generated output, fixtures, vendored code, and runtime state. Confirm flows from imports or call sites, not directory names. Treat unavailable symbol tooling as a limitation, not a reason to fetch it.

## Exit evidence

Report:

- primary entry points and commands;
- module ownership and responsibilities;
- key data or control flows;
- external boundaries and configuration inputs;
- relevant tests and verification commands;
- unresolved or inferred relationships, labeled clearly.

Keep the map skimmable and link conclusions to paths. Do not turn it into an architecture proposal.

When documentation is insufficient and the user needs dependency implementation source, read [Clone dependency source](references/clone-dependency.md) before using the OMCS clone tool.

## Next gate

Hand an ambiguity to `context`, a seam decision to `codebase-design`, or a reproducible defect to `diagnose`.

From Rafcin/oh-my-codex-slim, MIT.

More from Rafcin/oh-my-codex-slim

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 26, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Rafcin/oh-my-codex-slim
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Rafcin

Cite this page

codemap skill. Agent Mart. https://agentmart.dev/skills/rafcin-codemap (last updated 2026-10-24)