What is cartograph CLAUDE.md?

A project guide for Cartograph, an MCP server and command-line tool that analyzes a codebase and maps how its files depend on one another. MCP is a way for AI agents to call tools provided by another program.

Use it to inspect repository structure, rank important files, trace dependencies, find connections between code elements, or run Cartograph's CLI and MCP server.

It helps agents find the important parts of a repository without loading every file, which reduces irrelevant context during coding tasks.

How anthony-maio/cartograph configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to anthony-maio/cartograph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/anthony-maio/cartograph/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/anthony-maio/cartograph

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anthony-maio/cartograph/claude-md.svg)](https://agentmods.dev/instructions/anthony-maio/cartograph/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/anthony-maio/cartograph/claude-md"><img src="https://agentmods.dev/badge/instructions/anthony-maio/cartograph/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 746 This file is loaded in full into every session.

When invoked 746 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00746	$0.00746
Opus 5	$0.00373	$0.00373
Sonnet 5	$0.00149	$0.00149
Haiku 4.5	$0.00075	$0.00075

Measured 7d ago against content hash abcb3ceb2871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cartograph 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 7d 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Project Is

Cartograph is an MCP server + CLI tool for intelligent codebase analysis. It scores files by importance (entry points, fan-in, exports), maps dependencies, and provides targeted context for AI agents. Instead of dumping an entire repo, it gives agents only what matters.

Two modes:

MCP server (src/mcp.ts) — Tools that AI agents call directly. No external LLM needed since the agent IS the LLM.
CLI (src/cli.ts) — Standalone tool with optional LLM-powered synthesis via Gemini/OpenAI/OpenRouter.

Commands

npm install          # Install dependencies
npm run dev -- <args>  # Run CLI in dev mode (e.g. npm run dev -- . --static)
npm run dev:mcp      # Run MCP server in dev mode
npm run build        # Bundle both CLI and MCP server to dist/
npm run start -- <args>  # Run built CLI
npm run start:mcp    # Run built MCP server
npm run check        # TypeScript type-check (no emit)

MCP Server

The MCP server can be registered in a Claude Code or Claude Desktop config. It exposes two tools:

analyze_repo — Full static analysis: scored file list, dependency graph, top N file contents. Accepts local path or GitHub URL.
get_file_contents — Read specific files from a repo. Use after analyze_repo to drill into files of interest.

CLI Usage

cartograph <repo> [options]

# Static mode (no LLM, no API key)
cartograph ./my-project --static -o analysis.md

# Full LLM analysis
cartograph ./my-project -p gemini -k $CARTOGRAPH_API_KEY -o wiki.md

# Context selection — only files needed for a task
cartograph ./my-project -c "add user authentication" -p gemini -k $CARTOGRAPH_API_KEY

Providers: gemini (default), openai, openrouter. Key via --key or CARTOGRAPH_API_KEY env var.

Architecture

All source in src/. Two entry points, shared core.

Core (pure logic, no web deps):

src/analyzer.ts — Git clone, file walking, import/export extraction, importance scoring heuristics
src/schema.ts — All TypeScript types, Zod schemas, provider/model config
src/pipeline.ts — LLM-powered 3-pass pipeline (summarize → synthesize → context select)
src/llm.ts — Unified LLM client (Gemini native SDK, OpenAI/OpenRouter via OpenAI SDK)
src/markdown.ts — Serializers for wiki/static/context output formats

Read the full file on GitHub · 67 lines

Changes

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.

7d ago First seen · 67 lines · 746 tokens per session scan A abcb3ceb2871

Subscribe to this mod's changes

cartograph CLAUDE.md is an instructions file published in the GitHub repository anthony-maio/cartograph (3 stars, last pushed 4mo ago), licensed MIT. It adds 746 tokens to every session, about $0.0037 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.

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

cartograph: Instructions file for Claude Code