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 skills add bjornj12/golf-coach --skill trackman-session-analyzergit 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/skills/bjornj12/golf-coach/trackman-session-analyzer)<a href="https://agentmods.dev/skills/bjornj12/golf-coach/trackman-session-analyzer"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/trackman-session-analyzer/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/skills/bjornj12/golf-coach/trackman-session-analyzer"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/trackman-session-analyzer.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 | $0.00097 | $0.01279 |
| Opus 5 | $0.00048 | $0.00639 |
| Sonnet 5 | $0.00019 | $0.00256 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
trackman-session-analyzer 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trackman Session Analyzer
Ingests the user's recent Trackman sessions, stores a deterministic analysis of each in the MCP's local store (capped at the last 30, newest first), and returns a summary of the most recent session with its stats normalized against prior sessions.
<HARD-RULE: RUN IN A FORK, NEVER ON THE MAIN THREAD> This is a data-collection skill. It makes many MCP calls and pulls large shot-level payloads that would bloat the main conversation. The main agent must NOT execute the steps below inline.
Instead, the main agent's ONLY job is to dispatch a single subagent (the
Agent/Task tool, general-purpose type) whose prompt is "Follow the
trackman-session-analyzer skill end to end and return only the final summary."
The subagent does all the work in its own context and returns just the summary
section. If you are the dispatched subagent, proceed with the workflow.
Inputs / tools used (all from the golf-coach MCP)
auth, trackman(action="sessions"), session_analysis(action="analyze"),
session_analysis(action="list"), session_analysis(action="get"). The heavy lifting (classify,
metrics, course difficulty, normalization, used-vs-available clubs) is done
deterministically inside session_analysis(action="analyze") — your job is orchestration
and narration, not recomputing numbers.
Workflow (subagent)
-
Auth check. Call
auth. If not authenticated, stop and report that the user needs to rungolf-coach login— do not fabricate data. -
Pull recent sessions. Call
trackman(action="sessions", take=30)(newest first). This includes both practice activities and course rounds. -
Find what's new. Call
session_analysis(action="list")to get already-stored ids. -
Analyze + store new sessions, OLDEST first. Reverse the fetched list and walk it oldest → newest. For each session whose id is not already stored, call
session_analysis(action="analyze", activity_id). Oldest-first matters: each session is normalized against the sessions chronologically before it, so the history must already be stored when the newest session is analyzed. The store keeps only the last 30. Skip nothing silently — if a call errors, note it and continue.
What ships with it
1 file 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.
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.
- 10d ago First seen · 101 lines · 97 tokens per session scan A bdc6e5f34bc1
trackman-session-analyzer is a skill published in the GitHub repository bjornj12/golf-coach (1 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,279 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…