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 skills add chemrich/cabineteer --skill drive-mcp-handlersgit clone --depth 1 https://github.com/chemrich/cabineteerWrote 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/skills/chemrich/cabineteer/drive-mcp-handlers)<a href="https://agentmods.dev/skills/chemrich/cabineteer/drive-mcp-handlers"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/drive-mcp-handlers/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/skills/chemrich/cabineteer/drive-mcp-handlers"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/drive-mcp-handlers.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 | $0.00102 | $0.00757 |
| Opus 5 | $0.00051 | $0.00378 |
| Sonnet 5 | $0.00020 | $0.00151 |
| Haiku 4.5 | $0.00010 | $0.00076 |
Grade A, and why
drive-mcp-handlers 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 12d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving tool handlers directly
Every MCP tool is a plain async handler named _tool_<name> in src/cabineteer/server.py that takes an args dict and returns list[types.TextContent] whose [0].text is a JSON string. You can call these without any MCP client — this bypasses the transport entirely and always runs the current on-disk code, even when the session's registered cabinet server process is stale.
Pattern
import asyncio, json
from cabineteer import server as srv
res = asyncio.run(srv._tool_evaluate_cabinet({"width": 600, "height": 720, "depth": 550}))
print(json.loads(res[0].text)["summary"]) # {'errors': 0, 'warnings': 0, 'info': 0, 'pass': True}
Run it with uv run python - <<'EOF' ... EOF (or uv run python -c "...").
Handler names
The tool name usually maps to _tool_<name> — e.g. design_cabinet → _tool_design_cabinet, generate_cutlist → _tool_generate_cutlist, visualize_project → _tool_visualize_project. There are exceptions (e.g. list_joinery_options → _tool_list_joinery), so the eval harness's TOOL_DISPATCH (in evals/harness.py) is the canonical name→handler map — check it rather than assuming the pattern.
Args
The args dict mirrors the tool's inputSchema in server.py. Cabinet geometry uses drawer_config as a list of [height_mm, opening_type] pairs (e.g. [[300, "drawer"], [192, "drawer"]]); opening_type is one of drawer | door | door_pair | shelf | open. All units are millimetres.
Why this matters here
- Stale server: the session's
cabinetserver only picks up merged code after a/mcpreconnect. Direct-drive sidesteps that — use it to verify a fix landed before reconnecting. - Reproducing evals: copy a scenario's
argsfromevals/scenarios.pyand drive the handler to see the full JSON result an assertion walked (evals only surface the failing path). - File-writing tools write under
~/.cabineteer/. Thevisualize_*tools accept an explicitoutput_dir— point it at a scratch path when probing.generate_cutlist/generate_project_cutlisthave nooutput_dir(they always write to~/.cabineteer/cutlists/, and passingoutput_dirraisesValueError: Unknown cabinet parameter(s)); use a throwawaynameif you want to avoid clobbering. Outputnameis validated as a filename stem (no../separators) — a traversal name raises.
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.
- 12d ago First seen · 35 lines · 102 tokens per session scan A df3e53b75ba1
drive-mcp-handlers is a skill published in the GitHub repository chemrich/cabineteer (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 102 tokens to every session and 757 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…