Borrowing it
Nothing to install: this file belongs to builditwithgk/repo-cartographer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/builditwithgk/repo-cartographer/main/CLAUDE.mdgit clone --depth 1 https://github.com/builditwithgk/repo-cartographerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/builditwithgk/repo-cartographer/claude-md)<a href="https://agentmods.dev/instructions/builditwithgk/repo-cartographer/claude-md"><img src="https://agentmods.dev/badge/instructions/builditwithgk/repo-cartographer/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/builditwithgk/repo-cartographer/claude-md"><img src="https://agentmods.dev/badge/instructions/builditwithgk/repo-cartographer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01083 | $0.01083 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
repo-cartographer CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — repo-cartographer
What this is
An MCP (Model Context Protocol) server that helps any LLM understand a codebase and produce an architecture diagram for it. Tagline: "Understand any codebase in 60 seconds."
It is model-agnostic: it works with any MCP client (Claude Code, Claude Desktop, ChatGPT/OpenAI Agents SDK, Cursor, Copilot, Cline, etc.). Do NOT add any Claude-specific dependency.
Core design principle (do not violate)
The server does deterministic extraction only. The model does the reasoning. The server must never try to semantically "understand" code. It parses hard facts (file tree, import edges, manifests, framework detection, entry points) and returns structured JSON. The connected LLM turns those facts into the diagram and narrative.
This split is intentional: it keeps the server simple, testable, and portable, and it is the main selling point when people evaluate the project.
Tech
- TypeScript, ESM ("type": "module").
- @modelcontextprotocol/sdk (stdio transport).
- zod for input validation.
- No heavy parsers required. Prefer lightweight regex / line scanning. Optional: es-module-lexer for JS/TS imports. Keep dependencies minimal.
Scope (MVP — must stay small, ~2 day build)
- Languages: JavaScript/TypeScript and Python only for v1.
- Handle large repos by SUMMARIZING (cap files scanned, skip node_modules, .git, dist, build, venv, pycache, vendor). Never dump every file.
- Everything runs locally against a filesystem path. No network calls.
Tools to implement (build & test one at a time)
scan_repo(path)-> JSON:- detected languages, frameworks (from package.json / pyproject.toml / requirements.txt / common config files),
- top-level modules/directories with short role guesses,
- entry points (main, index, main, bin, scripts),
- manifest summary (name, deps).
build_import_graph(path)-> JSON:- nodes = files/modules, edges = import/require relationships (JS/TS + Py).
- collapse to module/directory level when the file count is large.
generate_diagram(path, level)-> string:- combine scan + import graph into a DRAFT Mermaid flowchart.
level= "high" (dirs/services) | "detail" (files). Default "high".- This is a draft the model is expected to refine.
render_diagram(mermaid, outPath):- write a self-contained .html that renders the Mermaid via CDN, plus the raw .mermaid file. This HTML is the shareable artifact — make it look good.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 100 lines · 1,083 tokens per session scan A 5de6e674f03d
repo-cartographer CLAUDE.md is an instructions file published in the GitHub repository builditwithgk/repo-cartographer (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,083 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).