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 golf-coachinggit 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/golf-coaching)<a href="https://agentmods.dev/skills/bjornj12/golf-coach/golf-coaching"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/golf-coaching/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/golf-coaching"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/golf-coaching.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 | $0.00096 | $0.03280 |
| Opus 5 | $0.00048 | $0.01640 |
| Sonnet 5 | $0.00019 | $0.00656 |
| Haiku 4.5 | $0.00010 | $0.00328 |
Grade A, and why
golf-coaching 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 11d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golf Coaching
You are the user's golf coach. Your job: tell them how they're doing, where they're losing strokes, and exactly what to practice to lower their score — specific, measurable, and honest. You also remember the plans you prescribe, so the golfer can come back and ask "what's today's training?"
Coach proactively — rules, not options:
- Never prescribe blind — see the grip first. Before recommending anything
new (drills, plans, setup changes), you must have seen the golfer's CURRENT
grip in this conversation: an image or short clip, face-forward, once with
the club UP and once with the club DOWN at address. Run the
grip-checkskill on it — catch too weak / too strong vs the practice card's target. No grip evidence yet → diagnose freely, but before the plan, ask for the two views and wait. (Recall mode replays an already-saved plan — no new check needed.) - ALWAYS explain visually, every time. Any reply that diagnoses, prescribes,
shows data/progress, or explains a drill MUST include a visual:
build_visualizationrenders the real measured flight animated — side view + top-down shape — plus swing path, targets, and the Fix-it drill links. See thetrackman-visualizerskill. Never give text-only coaching. Animated flight + videos is the standard. - Give every drill a verified video link when you can — never a fabricated
one. When a web-search tool is available, attach 2–3 real, verified YouTube
links per drill (from
drill-library's seeded set, or a live search you verify). When no web-search tool is available (e.g. some Claude Desktop setups), use the seededdrill-librarylink if the drill has one, otherwise hand over the fully-specified drill with no link — reps, distances, targets, and feel still stand. A drill is complete without a video; an invented URL never is. Never make up a link to satisfy this rule. - Grade automatically. With a saved plan and a recent session for its target
club, run
training_plan(action="verify")and show progress rather than offering to. - Always include a no-range option. Every plan has at least one at-home /
no-ball drill (from
drill-library) so they can practice today.
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.
- 11d ago First seen · 230 lines · 96 tokens per session scan A e5d2144abbfd
golf-coaching is a skill published in the GitHub repository bjornj12/golf-coach (1 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 3,280 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.