cabineteer: Instructions file for Claude Code

CLAUDE.md

cabineteer CLAUDE.md is an instructions file for Claude Code from chemrich/cabineteer. It costs 17,505 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Cabineteer, a tool that helps design and check items such as cabinets and drawers, including their parts lists. They document full and lightweight installations and ways to run its MCP server, a connection that lets AI tools call it.

In plain words
What is it for?
Use them to install Cabineteer, start its server for Claude Desktop or Gemini CLI, run it over HTTP, test the project, and run filtered evaluations.
Why use it?
They explain which dependencies and commands to use, including a lighter setup that skips optional computer-aided design and packing tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is chemrich/cabineteer's own configuration. It tells Claude Code how to work on cabineteer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cabineteer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chemrich/cabineteer. 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/chemrich/cabineteer/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chemrich/cabineteer

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.

agentmods badge for cabineteer CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chemrich/cabineteer/claude-md/github.svg)](https://agentmods.dev/instructions/chemrich/cabineteer/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chemrich/cabineteer/claude-md"><img src="https://agentmods.dev/badge/instructions/chemrich/cabineteer/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.

agentmods 80×15 button for cabineteer CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chemrich/cabineteer/claude-md"><img src="https://agentmods.dev/badge/instructions/chemrich/cabineteer/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17,505 This file is loaded in full into every session.
When invoked 17,505 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.17505 $0.17505
Opus 5 $0.08752 $0.08752
Sonnet 5 $0.03501 $0.03501
Haiku 4.5 $0.01750 $0.01750

Measured 2d ago against content hash f6a4336202b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cabineteer 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 2d 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 · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 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

# Full install — CadQuery, opcut, rectpack, and dev tools (recommended)
uv pip install -e ".[full,dev]"

# Lite install — pure-Python only: parametric checks, cutlist BOM, MCP, evals
uv pip install -e .

# Or just sync everything via uv (default-groups = full + dev, so this is equivalent to full)
uv sync

# Run the MCP server (stdio, for Claude Desktop / Gemini CLI)
uv run cabineteer

# Lite mode — skips CadQuery, opcut, and rectpack
uv run --no-group full cabineteer

# Run the MCP server (HTTP/SSE, port 3749 auto-incrementing)
uv run cabineteer --http
uv run cabineteer --http --port 4200

# Run tests
uv run pytest tests/ -v

# Run a single test file
uv run pytest tests/test_evaluation.py -v

# Run a single test by name
uv run pytest tests/test_evaluation.py -v -k "test_valid_drawer"

# Run evals (full suite)
uv run python -m evals

# Run evals with filters
uv run python -m evals --tag kitchen
uv run python -m evals --tag drawer --tag door
uv run python -m evals --difficulty advanced
uv run python -m evals --name overflow_drawer_stack
uv run python -m evals --json          # machine-readable
uv run python -m evals --list          # print scenario catalogue

Architecture

The package lives in src/cabineteer/. All units are millimetres. The data-flow is:

hardware.py + joinery.py
        │
        ▼
cabinet.py / drawer.py / door.py   ← parametric dataclasses (no CadQuery required)
        │
        ▼
project.py      ← multi-cabinet projects, shared-design merge, persistence (no CadQuery required)
        │
        ▼
evaluation.py   ← returns typed Issue objects (no CadQuery required)
        │
        ▼
cutlist.py      ← BOM, guillotine optimiser, JSON/CSV export (no CadQuery required)
        │
        ▼
server.py       ← MCP server (30 tools, stdio or HTTP/SSE)

evals/ (harness + scenarios) imports server handler functions directly — no MCP transport involved — so the full eval suite runs in under 1 second.

Read the full file on GitHub · 222 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.

  1. 2d ago Changed · +3 lines · +1,916 tokens per session f6a4336202b0
  2. 8d ago First seen · 219 lines · 15,589 tokens per session scan A 84056addc72f

Subscribe to this mod's changes

cabineteer CLAUDE.md is an instructions file published in the GitHub repository chemrich/cabineteer (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17,505 tokens to every session, about $0.0875 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.

Related

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.

vercel/next.js · 7,296 tokens

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 · 5,153 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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens