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.
npx agentmods add instructions/paiml/rust-mcp-sdk/claude-mdgit clone --depth 1 https://github.com/paiml/rust-mcp-sdkWrote 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.
[](https://agentmods.dev/instructions/paiml/rust-mcp-sdk/claude-md)<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>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.
| Model | Per session | Once 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 |
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 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:
- Run locally to see which functions exceed cog 25:
pmat analyze complexity --format json --max-cognitive 25 \ | jq '.violations[] | select(.path | startswith("src/"))' - Apply one of the 6 refactor techniques (P1–P6) documented in
.planning/phases/75-fix-pmat-issues/75-RESEARCH.mdArchitecture Patterns. - 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). - 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.
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.
- 5d ago First seen · 665 lines · 10,210 tokens per session scan A 95b4b7aee7ab
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.
Other instructions, from other repositories
lineark CLAUDE.md
Instructions for flipbit03/lineark, covering claude.md — lineark, what is this, workspace layout, key commands and writing online tests: the three pillars.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
ton-rs AGENTS.md
AGENTS.md instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.