tool-agnostic-mcp-routing

tool-agnostic-mcp-routing is a skill for Claude Code, Codex from ntaffzii/Skill-Agents. It costs 56 tokens per session (1,294 once invoked), scanned A, original, MIT.

Guidance for choosing available agent or MCP tools by the capability needed, rather than by a fixed tool name. MCP is a way for agents to connect to external tools and services.

In plain words
What is it for?
Use it to map jobs such as inspecting code, editing files, running tests, reading project documentation, or checking version-control state to available tools.
Why use it?
It helps instructions keep working when different agents expose different names for file reading, editing, testing, or repository tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to map jobs such as inspecting code, editing files, running tests, reading project documentation, or checking version-control state to available tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing
Install

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.

Any agent
npx skills add ntaffzii/Skill-Agents --skill tool-agnostic-mcp-routing
Clone the repo
git clone --depth 1 https://github.com/ntaffzii/Skill-Agents

Made for: Claude Code, Codex.

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 tool-agnostic-mcp-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing/github.svg)](https://agentmods.dev/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing)
Your own site
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing/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 tool-agnostic-mcp-routing

Your own site · 80×15
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/tool-agnostic-mcp-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 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.
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 $0.00056 $0.01294
Opus 5 $0.00028 $0.00647
Sonnet 5 $0.00011 $0.00259
Haiku 4.5 $0.00006 $0.00129

Measured 11d ago against content hash 5c2ba426b8bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tool-agnostic-mcp-routing 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 11d 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.

Skill.md/tool-agnostic-mcp-routing/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool-Agnostic MCP Routing

Use this skill when the current environment may have different tool names than this repository.

Capability Map

Translate task needs into capabilities:

Need Capability
Inspect code file search, file read
Choose tool scope toolset recommender, toolset inspector, registry
Edit code patch, file write, code edit
Verify code command runner, test runner
Hand off blocked commands user-run script generator, command handoff planner, script risk validator
Plan validation validation planner, command policy checker
Inspect repository state version control status, diff, log
Control repository state branch creator, checkout, stage, unstage, commit
Understand project shape project stack, scripts, manifest inspection
Understand project docs documentation index, README/docs reader, context bundle
Build repo map repository index builder, symbol/file search, related-file finder
Compare external MCP ideas MCP catalog search, repo pattern comparison, local adaptation planner
Inspect dependencies package manager detection, dependency manifest reader, lockfile status
Inspect containers Docker CLI checker, Dockerfile inspector, Compose service inspector, Docker validation planner
Inspect API surface route finder, endpoint extractor, OpenAPI spec reader, API config hints
Inspect data layer schema finder, migration finder, ORM model extractor, database config hints
Query configured database read-only SQL planner, SQL risk explainer, read-only Postgres runner
Inspect configuration config finder, env key lister, secret hygiene checker
Inspect tests test file finder, framework detector, source-to-test mapper
Inspect CI CI file finder, GitHub Actions job inspector, validation command extractor
Inspect local tasks TODO/FIXME scanner, roadmap file finder
Inspect dependency risk unpinned dependency finder, high-risk dependency name checker
Scan repository security secret scanner, dangerous command scanner, env exposure scanner, security report
Inspect release readiness changelog finder, version detector, release checklist
Snapshot before broad edits backup planner, zip snapshot creator
Edit structured registries JSON/YAML/TOML reader, path getter, structured path patcher
Preserve project memory memory saver, memory search, project memory summary
Build personal context typed memory saver, context pack builder, memory handoff generator
Search long-running context vector or semantic memory search, related-memory finder, memory cluster summarizer
Build RAG context text chunker, RAG provider planner, embedding request planner, source metadata preserver
Inspect GitHub metadata workflow finder, Actions inspector, PR description drafter
Inspect GitHub API data repo reader, issue reader, PR reader, PR file lister, check status reader
Inspect browser/UI readiness browser capability checker, static HTML inspector, smoke-check planner
Map a web page HTML page mapper, heading/link/form/button extractor, element finder by label
Inspect live UI Playwright runtime checker, page inspector, screenshot capture
Automate live UI Playwright click, fill, text assertion, console/network failure inspector, accessibility snapshot, persistent session runner
Inspect design files Figma auth checker, design file summary, token/component extractor, frontend implementation planner
Try safe experiments sandbox workspace creator, snippet compiler, sandbox run planner
Understand tool failures audit log, policy denial inspection
Audit MCP safety risk classifier, mutating tool finder, policy coverage checker
Research current facts web search, URL fetch
Capture public web pages provider-neutral static fetch, browser capture, optional cloud scraper adapter, social public-only reader
Research finance markets market quote reader, crypto price reader, finance-news planner, watchlist summarizer, position-risk calculator
Work with Notion Notion auth checker, page search, page reader, note/update payload planner
Bridge Obsidian and Notion Obsidian note inspector, Notion payload planner, Markdown conversion planner, sync checklist
Work with chat apps Slack/Discord config checker, message search, channel summarizer, reply drafter, action-item extractor
Triage inbox email config checker, email search planner, email summarizer, action extractor, reply drafter
Plan calendar calendar config checker, event summarizer, daily plan builder, meeting prep drafter, follow-up extractor
Plan issue work issue reference parser, issue draft builder, task breakdown, issue update planner
Inspect UI browser automation, screenshot
Work with images/video media inspection, frame extraction
Improve prompts prompt analysis, rewrite, scoring
Save progress handoff, document write

Read the full file on GitHub · 109 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. 11d ago First seen · 109 lines · 56 tokens per session scan A 5c2ba426b8bb

Subscribe to this mod's changes

tool-agnostic-mcp-routing is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,294 once invoked, about $0.0003 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 skills, from other repositories

auto-research

Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.

sickn33/agentic-awesome-skills · 29 tokens

pake

Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…

tw93/Pake · 119 tokens

acceptance

End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real…

lobehub/lobehub · 163 tokens

sovereign-economics-engine

Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.

winstonkoh87/Athena-Public · 43 tokens

therapeutic-ifs

Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.

winstonkoh87/Athena-Public · 34 tokens

dashboard-builder

Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.

winstonkoh87/Athena-Public · 31 tokens