rust-mcp-sdk: Skill for Claude Code

.claude/skills/spike-findings-rust-mcp-sdk/SKILL.md

spike-findings-rust-mcp-sdk is a skill for Claude Code from paiml/rust-mcp-sdk. It costs 107 tokens per session (5,567 once invoked), scanned A, original, MIT.

An implementation plan for adding two capabilities to the PMCP Rust SDK: SEP-2640 Skills support and configurable MCP servers built from SQL, GraphQL, or OpenAPI schemas. A schema describes available data or API operations so tools can be generated without writing Rust for each one.

In plain words
What is it for?
Use it as a blueprint when implementing Skills support or building configurable MCP servers for SQL databases, GraphQL services, and OpenAPI-described APIs.
Why use it?
It records patterns already tested in experiments and clarifies how agent instructions, fallback MCP prompts, database connectors, and schema-based servers should fit into the SDK.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument; mentions Claude Code.

This is paiml/rust-mcp-sdk's own configuration. It tells Claude Code how to work on rust-mcp-sdk 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 rust-mcp-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to paiml/rust-mcp-sdk. 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/paiml/rust-mcp-sdk/main/.claude/skills/spike-findings-rust-mcp-sdk/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/paiml/rust-mcp-sdk

Made for: Claude Code.

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 spike-findings-rust-mcp-sdk

README.md
[![agentmods](https://agentmods.dev/badge/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk/github.svg)](https://agentmods.dev/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk)
Your own site
<a href="https://agentmods.dev/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk"><img src="https://agentmods.dev/badge/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk/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 spike-findings-rust-mcp-sdk

Your own site · 80×15
<a href="https://agentmods.dev/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk"><img src="https://agentmods.dev/badge/skills/paiml/rust-mcp-sdk/spike-findings-rust-mcp-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,567 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00107 $0.05567
Opus 5 $0.00053 $0.02783
Sonnet 5 $0.00021 $0.01113
Haiku 4.5 $0.00011 $0.00557

Measured 6d ago against content hash fbd6ad8ffa2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spike-findings-rust-mcp-sdk 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 6d 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.

.claude/skills/spike-findings-rust-mcp-sdk/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Two complementary additions to the PMCP SDK, validated across two spike sessions:

Session 1 (2026-05-12, spikes 001-002): SEP-2640 Skills support. Skills are rich, structured agent-workflow instructions discovered and consumed via existing MCP resources/* primitives — no new RPC methods, but two small additions to PMCP's protocol types are required. The DX layer provides Skill / SkillReference / Skills types and a bootstrap_skill_and_prompt(...) builder method that registers the same skill data under both a SEP-2640 surface AND a fallback MCP prompt surface, so hosts that don't yet support SEP-2640 still get the full bootstrap context in one round-trip.

Session 2 (2026-05-17, spikes 003-006): Schema-server toolkit lift. The pmcp-run service's three "built-in server" core crates (sql, graphql, openapi) let server authors build a complete MCP server from a schema file (SQL DDL / OpenAPI YAML / GraphQL SDL) plus a TOML config — no Rust code required for curated tools. The lift promotes the already- extracted proto-SDK (mcp-server-common, ~2.2k LoC) to a public PMCP workspace crate, ships per-backend connector crates with multi-dialect SQL support, AND ships a pmcp-config-helper MCP server with Type 2 SEP-2640 authoring Skills (consumed by end-users in their MCP client).

Session 3 (2026-09-01, spikes 008-011): Skills positioning. With the skills feature shipped (src/server/skills.rs, examples s44/c10), these spikes re-validated conformance against the CURRENT SEP-2640 draft (rewritten 2026-08-29: skills/list + skills/get now mandatory — the shipped module is non-conformant on the one thing it declares) and settled how Skills relate to the SDK's two other instruction-carrying mechanisms: prompts-as-workflows (SequentialWorkflow) and pmcp-agent. Verdict: three points on one execution-locus axis sharing one content type — the axis is WHERE JUDGMENT RUNS. Skill is the canonical content primitive the other two project to (workflow → skill) and consume from (agent ← pinned skill). Alongside, composing — never instead.

Spike sessions wrapped: 2026-05-12, 2026-05-17, 2026-09-01.

Read the full file on GitHub · 333 lines

Files

What ships with it

47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed · +106 lines · +19 tokens per session fbd6ad8ffa2e
  2. 11d ago First seen · 227 lines · 88 tokens per session scan A 77cc1662ac39

Subscribe to this mod's changes

spike-findings-rust-mcp-sdk is a skill published in the GitHub repository paiml/rust-mcp-sdk (53 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 5,567 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

azure-postgres-ts

Connect to Azure Database for PostgreSQL Flexible Server from Node.js/TypeScript using the pg (node-postgres) package. Use for PostgreSQL queries, connection pooling, transactions, and Microsoft Entra ID (passwordless) authentication. Triggers: "PostgreSQL", "postgres", "pg client", "node-postgres", "Azure PostgreSQL…

microsoft/skills · 94 tokens

azure-cosmos-rust

Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data. Triggers: "cosmos db rust", "CosmosClient rust", "document crud rust", "NoSQL rust", "partition key rust".

microsoft/skills · 56 tokens

azure-eventhub-rust

Azure Event Hubs library for Rust. Send and receive events for streaming data ingestion and batch processing. Triggers: "event hubs rust", "ProducerClient rust", "ConsumerClient rust", "send event rust", "streaming rust", "eventhub rust".

microsoft/skills · 58 tokens

convex-create-component

Designs and builds Convex components with isolated tables, clear boundaries, and app-facing wrappers. Use this skill when creating a new Convex component, extracting reusable backend logic into a component, building a third-party integration that owns its own tables, packaging Convex functionality for reuse, or when…

get-convex/convex-backend · 95 tokens

convex-quickstart

Initializes a new Convex project from scratch or adds Convex to an existing app. Use this skill when starting a new project with Convex, scaffolding with npm create convex@latest, adding Convex to an existing React, Next.js, Vue, Svelte, or other frontend, wiring up ConvexProvider, configuring environment variables…

get-convex/convex-backend · 108 tokens

convex-migration-helper

Plans and executes safe Convex schema and data migrations using the widen-migrate-narrow workflow and the @convex-dev/migrations component. Use this skill when a deployment fails schema validation, existing documents need backfilling, fields need adding or removing or changing type, tables need splitting or merging…

get-convex/convex-backend · 102 tokens