fastmcp: Skill for Claude Code

.agents/skills/docs/SKILL.md

docs is a skill for Claude Code, Codex from PrefectHQ/fastmcp. It costs 68 tokens per session (1,077 once invoked), scanned A, original, Apache-2.0.

A writing procedure for creating or revising documentation pages for the FastMCP website. It explains the site's page structure, writing style, accessibility checks, and release process.

In plain words
What is it for?
Use it when adding a FastMCP feature page, fixing documentation, auditing existing pages, or preparing a change for review and publication.
Why use it?
It reduces mistakes such as editing generated pages, putting a feature in the wrong place, writing incomplete code examples, or forgetting the checks needed before publication.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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

About the project

FastMCP is a Python framework for building Model Context Protocol applications, which connect language models with tools and data through servers and clients. Developers use it to expose Python functions as tools, connect to local or remote MCP servers, and build interactive tool interfaces. The catalogue includes eight skills, three instructions, two rules, one setting, and one hook for FastMCP.

PrefectHQ/fastmcp · 28,322 stars · on GitHub · gofastmcp.com

Reuse

Borrowing it

Nothing to install: this file belongs to PrefectHQ/fastmcp. 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/PrefectHQ/fastmcp/main/.agents/skills/docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PrefectHQ/fastmcp

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 docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/prefecthq/fastmcp/docs/github.svg)](https://agentmods.dev/skills/prefecthq/fastmcp/docs)
Your own site
<a href="https://agentmods.dev/skills/prefecthq/fastmcp/docs"><img src="https://agentmods.dev/badge/skills/prefecthq/fastmcp/docs/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 docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/prefecthq/fastmcp/docs"><img src="https://agentmods.dev/badge/skills/prefecthq/fastmcp/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 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 $0.00068 $0.01077
Opus 5.5 $0.00027 $0.00431
Sonnet 5.5 $0.00014 $0.00215
Haiku 4.5 $0.00007 $0.00108

Measured today against content hash 77898e31b27b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs 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 today.

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.

.agents/skills/docs/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FastMCP docs

The docs are a Mintlify site built from docs/ on published-docs, served at https://gofastmcp.com/docs. The separate PrefectHQ/gofastmcp-website repository deploys its main branch to Vercel, serves the root landing page, and proxies these docs under /docs. Author docs here on main; website changes belong in that repository. A page exists only when docs/docs.json lists it, and a feature exists only when a page documents it. docs/python-sdk/** is generated from docstrings by a bot; edit the docstring, not the page.

Procedure

  1. Find the owning page before creating one. rg -l "<feature>" docs --glob '!docs/python-sdk/**' --glob '!docs/v2/**' --glob '!docs/v3/**'. Extend it when the feature belongs to that page's subject; add a page when it has its own.
  2. Read two neighboring pages in the same docs.json group and match their section order and heading depth.
  3. Write the page with the template below. Explain why the feature exists before showing how, and keep the first code block small enough to read without scrolling.
  4. Make every code block runnable: imports present, names defined, one idea per block. Pull intermediate values into named variables instead of nesting calls.
  5. Run the checks in Verify and fix what they report.
  6. When the change is ready to ship, open a PR against main. Merged is not live: the site serves published-docs. A stable release from main opens a Publish FastMCP v<version> docs PR against published-docs that a maintainer merges; for a docs-only change between releases, follow "Publishing docs by hand" in .agents/skills/release/SKILL.md. Either way, the Deploy docs run's verdict is what says the site changed.

Template

---
title: Feature Name
sidebarTitle: Feature
description: One sentence a search result can show.
icon: some-fontawesome-icon
---

import { VersionBadge } from '/snippets/version-badge.mdx'

<VersionBadge version="<version that introduces the feature>" />

One paragraph on the problem this solves and when to reach for it.

## Basic usage

Explain what the example does, then show it.

```python
from fastmcp import FastMCP

Read the full file on GitHub · 84 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. today Changed 77898e31b27b
  2. 1mo ago First seen · 84 lines · 68 tokens per session scan A a90370db4bf4

Subscribe to this mod's changes

docs is a skill published in the GitHub repository PrefectHQ/fastmcp (28,322 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 1,077 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-20.

Related

docs compared with skills from other repositories

docs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docsPrefectHQ/fastmcpSkill28ktodayApache-2.0A68Claude Code, Codex
first-readerShubhamsaboo/awesome-llm-appsSkill144kyesterdayApache-2.0A174Claude Code, Codex
hugging-face-model-trainerpatchy631/ai-engineering-hubSkill41k5d agoMITA131Claude Code
hugging-face-datasetspatchy631/ai-engineering-hubSkill41k5d agoMITA49Claude Code
hugging-face-paper-publisherpatchy631/ai-engineering-hubSkill41k5d agoMITA42Claude Code
thinking-out-loudShubhamsaboo/awesome-llm-appsSkill144kyesterdayApache-2.0A206Claude Code, Codex
create-tech-designhumanlayer/humanlayerSkill13kyesterdayApache-2.0A16Claude Code, Codex