helix.mcp: Skill for Claude Code

.squad/skills/mcp-wire-format-trim/SKILL.md

mcp-wire-format-trim is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 0 tokens per session (3,970 once invoked), scanned A, original, MIT.

A method for reducing the size of MCP tool descriptions and response metadata while keeping the actual tool-call data unchanged. MCP metadata tells an AI client what tools accept and return.

In plain words
What is it for?
Use it to audit default tool annotations or remove an unnecessary output schema while manually preserving the response payload.
Why use it?
It removes repeated or low-value schema information from tool listings, reducing the data clients must process for very small results.

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/.squad/skills/mcp-wire-format-trim/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-wire-format-trim

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-wire-format-trim"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-wire-format-trim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,970 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 $0.00000 $0.03970
Opus 5 $0.00000 $0.01985
Sonnet 5 $0.00000 $0.00794
Haiku 4.5 $0.00000 $0.00397

Measured 10d ago against content hash ee1ddafe7ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-wire-format-trim 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 10d 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.

.squad/skills/mcp-wire-format-trim/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Wire-Format Trim

When to use

  • You need to reduce tools/list token/byte cost without changing tool behavior.
  • You are auditing MCP metadata bloat in McpServerTool attributes or auto-generated schemas.

Pattern 1: default-annotation audit

  1. Verify SDK defaults from the exact package version in use (ModelContextProtocol.Core source or reflection).
  2. Only remove attribute properties whose explicit value matches the SDK default.
  3. In SDK 1.3.0, the important defaults are:
    • OpenWorld = true
    • ReadOnly = false
    • Idempotent = false
    • Destructive = true
    • UseStructuredContent = false
  4. Consequence: OpenWorld=true is removable noise, but Destructive=false must stay.

Pattern 2: drop outputSchema while preserving wire payload

Use this only for tiny results where schema carries little value and you must keep the actual tool-call payload stable.

  1. Change the tool method return type to CallToolResult (or Task<CallToolResult>).
  2. Remove UseStructuredContent = true from the [McpServerTool] attribute so the SDK stops advertising outputSchema.
  3. Return CallToolResult manually with both:
    • Content = [new TextContentBlock { Text = JsonSerializer.Serialize(value, McpJsonUtilities.DefaultOptions) }]
    • StructuredContent = JsonSerializer.SerializeToElement(value, McpJsonUtilities.DefaultOptions)
  4. This keeps the tool-call JSON payload/structured content intact while shrinking tools/list.

Pattern 2b: minimal object outputSchema via an empty marker type (SDK 2.x)

Use when a tool must keep UseStructuredContent = true — because SDK 2.x picks the structuredContent envelope from the schema's objectness — but the detailed schema is not worth its fixed-context rent.

The rule that makes this safe: AIFunctionMcpServerTool.ShouldWrapValueForLegacyWire asks only whether the schema's type is object (or ["object","null"]). It never reads properties or required, and the C# SDK does no runtime validation of structuredContent against outputSchema. So {"type":"object"} is functionally equivalent to a full property mirror, at ~17 B instead of hundreds.

Read the full file on GitHub · 278 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. 10d ago First seen · 278 lines · 0 tokens per session scan A ee1ddafe7ff9

Subscribe to this mod's changes

mcp-wire-format-trim is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,970 tokens. 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.