mcp-tooling

mcp-tooling is a skill for Claude Code, OpenCode from MichelKerkmeester/skilled-agent-harness_spec-driven-loops. It costs 165 tokens per session (3,738 once invoked), scanned A, original, MIT.

A routing hub for MCP connectors, which are bridges between an AI agent and external tools such as browsers, ClickUp, Notion, and Obsidian.

In plain words
What is it for?
It is for browser debugging, task management, note management, and other workflows that depend on external MCP tools.
Why use it?
It selects the appropriate workflow for each request so the agent can use different connected services through one entry point.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: allowed-tools in frontmatter, but also installed under .opencode/. Also seen: mentions OpenCode.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .opencode/bin/compiled-route.cjs --hub mcp-tooling --prompt "<task>".

Good fit It is for browser debugging, task management, note management, and other workflows that depend on external MCP tools.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops
agentmods
npx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling

Made for: Claude Code, OpenCode.

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 mcp-tooling

README.md
[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling)
Your own site
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling/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 mcp-tooling

Your own site · 80×15
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00165 $0.03738
Opus 5 $0.00082 $0.01869
Sonnet 5 $0.00033 $0.00748
Haiku 4.5 $0.00016 $0.00374

Measured 8d ago against content hash 38a846574eac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-tooling 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 8d 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.

.opencode/skills/mcp-tooling/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tooling Hub (mcp-tooling)

One skill, five workflow bridges plus four design transports, one shared family: mcp identity. mcp-tooling is the public, advisor-routable home for every MCP tool bridge in this repo. Before routing, the hub reads hub-router.json to resolve a workflowMode, then delegates through mode-registry.json. This hub holds NO per-mode logic — each mode keeps its own contract in its packet, and the hub only routes by workflowMode. mcp-code-mode is the shared MCP execution substrate all modes reach through the unchanged code_mode registration key; it is external infrastructure, not a hub member, and stays a flat standalone skill.


1. WHEN TO USE

Use this skill (through the hub) for any MCP tool-bridge workflow. Invoke it as mcp-tooling; the hub classifies the request, resolves a mode key, and loads the matching nested packet.

Mode Kind Use it for Packet
mcp-chrome-devtools workflow Browser debugging and automation: screenshots, DOM inspection, console/network capture, Lighthouse, via CLI (bdg) with an MCP fallback mcp-tooling/mcp-chrome-devtools/
mcp-click-up workflow ClickUp task management: daily ops via cupt CLI, documents/goals/bulk ops via the official MCP mcp-tooling/mcp-click-up/
mcp-obsidian workflow Obsidian vault and note management plus Iconic data.json rulebook automation: headless notesmd-cli, app-backed obsidian CLI, and the cyanheads MCP mcp-tooling/mcp-obsidian/
mcp-aside-devtools workflow AI-browser automation via the Aside browser: agentic aside CLI tasks, deterministic aside repl evidence capture, aside mcp via Code Mode fallback mcp-tooling/mcp-aside-devtools/
mcp-notion workflow Notion workspace operations via the official @notionhq/notion-mcp-server (24 tools) over Code Mode, direct Notion API for 5 gaps, plus the data-source / property / relation / rollup knowledge layer mcp-tooling/mcp-notion/
mcp-figma (transport) transport Drive Figma Desktop from the terminal via figma-ds-cli — document mutation lands in Figma Desktop (local writes limited to explicit-path exports per the registry's workspaceWrites clarifier), always paired with sk-design-md-generator for a measured Style Reference mcp-tooling/mcp-figma/
mcp-refero (transport) transport Search real-app UI design references via the Refero MCP (Code Mode, read-only) — screens, flows, styles; always paired with sk-design-md-generator for a measured Style Reference mcp-tooling/mcp-refero/
mcp-mobbin (transport) transport App/screen/flow design research via the Mobbin MCP (Code Mode, read-only) — mobile UX patterns from real apps; always paired with sk-design-md-generator for a measured Style Reference mcp-tooling/mcp-mobbin/
mcp-magicpath (transport) transport Component, project, team, design-system and canvas lookup via the magicpath-ai Node CLI over Code Mode's UTCP cli transport (read-only; its provider ships no MCP server) mcp-tooling/mcp-magicpath/

Read the full file on GitHub · 197 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 197 lines · 165 tokens per session scan A 38a846574eac

Subscribe to this mod's changes

mcp-tooling is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 3,738 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens