Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/huginnindustries/codecartographer/claude-mdgit clone --depth 1 https://github.com/HuginnIndustries/CodeCartographerWrote 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/huginnindustries/codecartographer/claude-md)<a href="https://agentmods.dev/instructions/huginnindustries/codecartographer/claude-md"><img src="https://agentmods.dev/badge/instructions/huginnindustries/codecartographer/claude-md.svg" alt="Measured on agentmods" 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 | $0.01931 | $0.01931 |
| Opus 5 | $0.00966 | $0.00966 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
CodeCartographer 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 4d 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 — 83 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.
Commands
npm ci # install (lockfile-strict)
npm run build # tsc compile to dist/ (required before publish; CI runs this)
npm test # node --experimental-strip-types --test tests/*.test.mjs
npm run smoke # end-to-end MCP smoke test against the published npm package
# Run a single test file:
node --experimental-strip-types --disable-warning=ExperimentalWarning --test tests/pipeline-invariants.test.mjs
# Run the Pi extension locally against the in-tree source (no rebuild needed):
pi -e /absolute/path/to/CodeCartographer/extensions/codecarto/index.ts
Node >= 20 is the floor; CI tests on Node 22 and 24. There is no linter.
Architecture
CodeCartographer is one framework shipped through three delivery surfaces that produce byte-identical phase prompts and validation behavior. The numbering below reflects code-architecture (source-of-truth-out) ordering; the user-facing recommendation ordering in README.md is different — see "Surface priority" below.
.codecarto/— the drop-in template (Markdown + YAML, no executable code). This is both the source of truth committed in this repo and the directory that gets copied into a user's target repo oncodecarto-init.core/workspace.tsexposes it aspackagedWorkspaceDir, resolved at runtime by walking up fromcore/to find the nearestpackage.json.extensions/codecarto/— Pi extension. Registers/codecarto-*slash commands, runs phases as isolatedAgentSessionsub-agents (auto-runner.ts), renders the live widget (agent-widget.ts), and writes the HTML dashboard (dashboard-writer.ts). Thetool_callhook inindex.tsblocksbashoutright and confinesedit/writeto.codecarto/plus the configured library path.mcp-server/— MCP server exposing ten workflow and library operations as JSON-RPC tools over stdio. Never spawns sub-agents; returns prompt text for the host to dispatch.
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.
- 4d ago First seen · 83 lines · 1,931 tokens per session scan A 64f920875279
CodeCartographer CLAUDE.md is an instructions file published in the GitHub repository HuginnIndustries/CodeCartographer (4 stars, last pushed 5d ago), licensed MIT. It adds 1,931 tokens to every session, about $0.0097 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
Ix CLAUDE.md
Claude Code instructions for ix-infrastructure/Ix, covering project: ix (this repo), layout, commands, cli dev (from ix-cli/) and skill + tooling (from repo root).
reverse-engineering-assistant CLAUDE.md
Claude Code instructions for cyberkaida/reverse-engineering-assistant, covering claude.md, project overview, build and test commands, java extension (ghidra plugin) and set ghidra installation directory first.
reverse-engineering-assistant AGENTS.md
AGENTS.md instructions for cyberkaida/reverse-engineering-assistant, covering agents.md, project overview, build & test commands, building the extension and set the ghidra installation directory first.
reverse-engineering-assistant copilot-instructions.md
Copilot instructions for cyberkaida/reverse-engineering-assistant, a project described as: MCP server for reverse engineering tasks in Ghidra 👩💻.
TechDebtMCP CLAUDE.md
Instructions for PierreJanineh/TechDebtMCP, covering claude.md, build & test commands, gotchas, architecture and building the mcpb bundle.
TechDebtMCP copilot-instructions.md
Instructions for PierreJanineh/TechDebtMCP, covering ai agent instructions for tech debt mcp, project overview, architecture, copilot pr review workflow and before creating a pr.