golf: Instructions file for Claude Code

CLAUDE.md

golf CLAUDE.md is an instructions file for Claude Code from golf-mcp/golf. It costs 1,415 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for Golf, a Python framework that turns files describing tools, resources, and prompts into a runnable MCP server. MCP is a standard way for applications to provide tools and data to AI assistants.

In plain words
What is it for?
Use it when building, updating, testing, or debugging Golf-based MCP servers, especially around authentication and automatic component discovery.
Why use it?
It explains Golf's architecture, development commands, and important changes in version 0.2.x. This helps agents avoid outdated authentication settings, dependencies, and files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

Nothing to install: this file belongs to golf-mcp/golf. 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/golf-mcp/golf/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/golf-mcp/golf

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 golf CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/golf-mcp/golf/claude-md.svg)](https://agentmods.dev/instructions/golf-mcp/golf/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/golf-mcp/golf/claude-md"><img src="https://agentmods.dev/badge/instructions/golf-mcp/golf/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,415 This file is loaded in full into every session.
When invoked 1,415 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.01415 $0.01415
Opus 5 $0.00707 $0.00707
Sonnet 5 $0.00283 $0.00283
Haiku 4.5 $0.00142 $0.00142

Measured today against content hash fddd7278f903, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

golf CLAUDE.md 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.

CLAUDE.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Golf is a Python framework for building MCP (Model Context Protocol) servers with zero boilerplate. It automatically discovers, parses, and compiles Python files containing tools, resources, and prompts into a runnable FastMCP server.

Authentication Compatibility

Golf 0.3.x targets FastMCP 4.0.0 and MCP 2026-07-28 while retaining FastMCP's legacy-client compatibility:

  • Authentication System: Complete rewrite using FastMCP's built-in auth providers (JWT, OAuth, Static tokens)
  • Legacy OAuth Removed: Custom OAuth implementation replaced with standards-compliant FastMCP providers
  • Configuration Changes: auth.py configuration must be updated to use new auth configs (legacy pre_build.py supported)
  • Dependency Updates: Requires exactly FastMCP 4.0.0, Python >=3.10, and Pydantic >=2.12
  • Removed Files: Legacy oauth.py and provider.py files removed from auth module
  • Deprecated Functions: get_provider_token() and OAuth-related helpers return None (legacy compatibility)

Key Architecture

  • Component Discovery: Golf automatically scans tools/, resources/, and prompts/ directories for Python files
  • Code Generation: The ManifestBuilder in src/golf/core/builder.py generates FastMCP server code from parsed components
  • CLI Interface: Entry point is src/golf/cli/main.py with commands: init, build, run
  • Configuration: Project settings managed via golf.json files, parsed by src/golf/core/config.py
  • Authentication: JWT/OAuth auth using FastMCP 4.0.0 providers in src/golf/auth/
  • Telemetry: Anonymous usage tracking with OpenTelemetry support in src/golf/telemetry/

Common Development Commands

Testing

# Run all tests with coverage
make test
# OR directly:
python -m pytest tests/ -v --cov=golf --cov-report=term-missing --cov-report=html

# Run tests without coverage (faster)
make test-fast
# OR directly:
python -m pytest tests/ -v

Read the full file on GitHub · 159 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 · -5 lines · +40 tokens per session fddd7278f903
  2. yesterday Changed · +3 lines · +53 tokens per session fb36b77366e2
  3. 6d ago First seen · 161 lines · 1,322 tokens per session scan A 62708487c1f2

Subscribe to this mod's changes

golf CLAUDE.md is an instructions file published in the GitHub repository golf-mcp/golf (839 stars, last pushed today), licensed Apache-2.0. It adds 1,415 tokens to every session, about $0.0071 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens