Borrowing it
Nothing to install: this file belongs to bjornj12/golf-coach. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bjornj12/golf-coach/main/CLAUDE.mdgit clone --depth 1 https://github.com/bjornj12/golf-coachWrote 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/bjornj12/golf-coach/claude-md)<a href="https://agentmods.dev/instructions/bjornj12/golf-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/bjornj12/golf-coach/claude-md/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.
<a href="https://agentmods.dev/instructions/bjornj12/golf-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/bjornj12/golf-coach/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04913 | $0.04913 |
| Opus 5 | $0.02457 | $0.02457 |
| Sonnet 5 | $0.00983 | $0.00983 |
| Haiku 4.5 | $0.00491 | $0.00491 |
Grade A, and why
golf-coach 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golf Coach
Project Overview
Name: Golf Coach (product name). The technical ids stay golf-coach (MCP
server / plugin) and golf-coach (published package / module golf_coach) —
these are deliberately NOT renamed, so existing installs and the registry entry
keep working. "Trackman" references to the data source also stay (it genuinely
connects to Trackman).
Purpose: A Model Context Protocol (MCP) server that connects to Trackman's golf platform using the user's own login, fetches their stats (course rounds, practice sessions, shot-level launch-monitor data, club gapping, handicap), and exposes them as MCP tools. On top of that data, a set of Claude skills act as the user's golf coach — diagnosing weaknesses and giving actionable, specific practice plans with example drills and YouTube links to follow.
Who it's for: The individual golfer who already practices on Trackman bays / ranges or plays Trackman-enabled courses, and wants their data turned into a concrete "what should I work on next" plan.
The Core Boundary (read this first)
There is a hard separation of concerns. Respect it in every change:
- The MCP server only fetches and returns raw data. Authentication, HTTP calls to Trackman, and shaping responses into clean JSON. It contains no coaching opinions, no drill recommendations, no analysis verdicts.
- The Claude skills do all the thinking. They call the MCP tools to get data, then diagnose, plan, and coach in prompt/markdown.
Why: coaching logic should be tunable by editing markdown, not redeploying a server. Keep judgment out of the server and data out of the skills.
Note on delivery (not a boundary break): the server serves the skill
markdown as MCP prompts (see prompts.py) so the coaching brain is available
in any MCP client, not only the Claude Code plugin. This is transport, not logic:
the server still computes no verdicts — it hands Claude the same skill text the
plugin would. The single source of truth stays in skills/.
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.
- 9d ago First seen · 342 lines · 4,913 tokens per session scan A 3e63517c1ec9
golf-coach CLAUDE.md is an instructions file published in the GitHub repository bjornj12/golf-coach (1 stars, last pushed 1mo ago), licensed MIT. It adds 4,913 tokens to every session, about $0.0246 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.