helix.mcp: Skill for Claude Code

.copilot/skills/mcp-tool-routing-copy/SKILL.md

mcp-tool-routing-copy is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 33 tokens per session (512 once invoked), scanned A, original, MIT.

A guide for writing MCP tool descriptions and error messages that help callers choose the right next tool. MCP tools are callable functions that connect an AI system to external services or workflows.

In plain words
What is it for?
Use it when improving tool descriptions, help guides, failure messages, or tests that check whether callers are directed through the correct workflow.
Why use it?
It reduces wasted attempts when tools only work for certain repositories, environments, or available files. Clear routing tells the caller what to use first and what to try after a predictable failure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is lewing/helix.mcp's own configuration. It tells Claude Code and Codex how to work on helix.mcp 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 helix.mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lewing/helix.mcp. 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/lewing/helix.mcp/main/.copilot/skills/mcp-tool-routing-copy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lewing/helix.mcp

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 mcp-tool-routing-copy

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-tool-routing-copy"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-tool-routing-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 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 $0.00033 $0.00512
Opus 5 $0.00016 $0.00256
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 11d ago against content hash 8a6b0f0e48ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-tool-routing-copy 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.

.copilot/skills/mcp-tool-routing-copy/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Use this when an MCP surface already has the needed tools, but callers still waste rounds because they cannot tell which tool to start with or what to do after a predictable failure. The goal is discoverability through copy, not a bigger tool surface.

Patterns

  • Lead with the behavioral contract: what the tool is for, and when it is the right first move.
  • If the tool only works for a subset of repos/pipelines/artifact layouts, say that explicitly in the description.
  • In failure messages, route to the next concrete tool sequence instead of stopping at “not found” or “unsupported”.
  • Keep the routing concise: “use X when / otherwise use Y” beats long implementation detail.
  • Mirror the same routing story across related surfaces such as tool descriptions, guide tools, and built-in help text.
  • Add regression tests at the copy seam: reflect method-level DescriptionAttribute text for MCP tools, and assert guide/help section order so routing guidance stays ahead of deep detail.
  • For false-confidence risks, test both the success-selection copy and the failure-path copy; a warning without the next tool sequence is not enough.

Examples

  • A structured-results tool says it parses Helix-hosted results when present, but directs callers to a build-system results API when those files are usually absent.
  • A log-search tool says it is the remote-first path for console investigation and points callers to a guide tool for repo-specific search patterns.
  • A repo guide adds a short “Start Here” section before deeper details so callers can choose the correct workflow quickly.
  • A regression test reflects an MCP method description and asserts it still says “substring search, not regex” plus the repo-specific fallback/selection wording.
  • A guide-rendering test verifies the “use AzDO results here” line appears before search-pattern inventories and that the recommended order pivots to structured results before log scraping.

Anti-Patterns

  • Warning that a tool “may fail” without naming the fallback tool or workflow
  • Burying the workflow choice after long inventories or implementation notes
  • Adding a composite tool before tightening the routing copy on the existing tools
  • Letting descriptions, guide output, and built-in help drift into different stories

Read the full file on GitHub · 33 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 · 33 lines · 33 tokens per session scan A 8a6b0f0e48ce

Subscribe to this mod's changes

mcp-tool-routing-copy is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 512 once invoked, about $0.0002 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.