rust-mcp-sdk CLAUDE.md

rust-mcp-sdk CLAUDE.md is an instructions file for coding agents from paiml/rust-mcp-sdk. It costs 10,210 tokens per session, scanned A, original, MIT.

Repository instructions for developing a Rust software development kit, including formatting, linting, builds, documentation tests, and CI checks.

In plain words
What is it for?
Use them when changing the Rust SDK, preparing a commit, or checking whether a pull request meets the repository's required gates.
Why use it?
They make quality checks part of committing and merging code, catching defects before changes are accepted.

Instructions file

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.

agentmods
npx agentmods add instructions/paiml/rust-mcp-sdk/claude-md
Clone the repo
git clone --depth 1 https://github.com/paiml/rust-mcp-sdk

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 rust-mcp-sdk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paiml/rust-mcp-sdk/claude-md.svg)](https://agentmods.dev/instructions/paiml/rust-mcp-sdk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paiml/rust-mcp-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/paiml/rust-mcp-sdk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 10,210 This file is loaded in full into every session.
When invoked 10,210 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.10210 $0.10210
Opus 5 $0.05105 $0.05105
Sonnet 5 $0.02042 $0.02042
Haiku 4.5 $0.01021 $0.01021

Measured 5d ago against content hash 95b4b7aee7ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-mcp-sdk CLAUDE.md scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

crates.io API (`curl -s https://crates.io/api/v1/crates/<name>/versions`), NOT
CLAUDE.md · 665 lines

How it starts

The opening of the file, as written. The whole thing — 665 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PMCP SDK Development Standards

Toyota Way Quality System - ZERO TOLERANCE FOR DEFECTS

We have ZERO tolerance for defects. Your "clippy warnings won't..." is a P0 problem.

Quality Gate Enforcement

Pre-Commit Quality Gates (MANDATORY)

ALL commits are blocked until quality gates pass:

  • Pre-commit hook automatically runs Toyota Way quality checks
  • Format checking: cargo fmt --all -- --check
  • Clippy analysis: Zero warnings allowed
  • Build verification: Must compile successfully
  • Doctest validation: All doctests must pass

To commit code:

make quality-gate  # Run before any commit
git add -A
git commit -m "message"  # Will be blocked if quality fails

CI Quality Gates (PR-blocking, added Phase 75 Wave 5)

PRs are blocked from merging if PMAT detects new cognitive-complexity violations.

The check runs in .github/workflows/ci.yml quality-gate job:

pmat quality-gate --fail-on-violation --checks complexity

PMAT version is pinned to 3.15.0 (matches .github/workflows/quality-badges.yml; see Phase 75 Wave 0 Task 3 for rationale). The gate aggregate job lists quality-gate in its needs: array, so a PMAT failure propagates to the org-required gate status check and blocks merge.

If your PR fails this check:

  1. Run locally to see which functions exceed cog 25:
    pmat analyze complexity --format json --max-cognitive 25 \
      | jq '.violations[] | select(.path | startswith("src/"))'
    
  2. Apply one of the 6 refactor techniques (P1–P6) documented in .planning/phases/75-fix-pmat-issues/75-RESEARCH.md Architecture Patterns.
  3. If the function is irreducibly complex (parser, AST walker, protocol dispatch), apply a // Why: annotated #[allow(clippy::cognitive_complexity)] per the template in .planning/phases/75-fix-pmat-issues/75-00-PLAN.md. Hard cap is cog 50 (D-03).
  4. Re-push and the gate re-runs.

DO NOT disable, weaken, or remove this gate without explicit Phase-level approval — it is the mechanism that keeps the README "Quality Gate: passing" badge accurate.

Read the full file on GitHub · 665 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. 5d ago First seen · 665 lines · 10,210 tokens per session scan A 95b4b7aee7ab

Subscribe to this mod's changes

rust-mcp-sdk CLAUDE.md is an instructions file published in the GitHub repository paiml/rust-mcp-sdk (53 stars, last pushed 4d ago), licensed MIT. It adds 10,210 tokens to every session, about $0.0510 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.