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 gamebook-screenshot-analysisgit 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/gamebook-screenshot-analysis)<a href="https://agentmods.dev/skills/bjornj12/golf-coach/gamebook-screenshot-analysis"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/gamebook-screenshot-analysis/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/gamebook-screenshot-analysis"><img src="https://agentmods.dev/badge/skills/bjornj12/golf-coach/gamebook-screenshot-analysis.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 | $0.00086 | $0.01386 |
| Opus 5 | $0.00043 | $0.00693 |
| Sonnet 5 | $0.00017 | $0.00277 |
| Haiku 4.5 | $0.00009 | $0.00139 |
Grade A, and why
gamebook-screenshot-analysis 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GameBook Screenshot Analysis
Turn the user's Golf GameBook screenshots into a structured on-course round the coach can use. GameBook has no export/API, but the data is on the user's phone as screenshots — read them directly.
The one rule that governs everything
GameBook reliably records only score-per-hole. Putts, fairways, GIR, chips, bunkers, scrambling, up-and-down and sand saves are only as complete as what the golfer tapped in during the round. Never analyze a dimension that wasn't really tracked. A "0.0%" sand-save/up-and-down/scrambling with no supporting hole data means "not entered," not a genuine zero. Flag coverage; do not invent.
Run this off the main thread
This reads several images (large tokens). In Claude Code, the main agent should
dispatch ONE fresh subagent (Task/Agent tool, general-purpose) whose prompt is:
"Follow the gamebook-screenshot-analysis skill end to end on these image paths:
and return only the final summary." The subagent does the work and
returns just the summary. If you are that dispatched worker, proceed.
Reading the screens (legend)
- Header: the big number is gross (it may sit partly behind the "Net score" label — it's still the round total; confirm it equals Out+In). "Net score" + a coloured +/- chip = net and net-to-par. "Position x/y" = group finish.
- Scorecard rows: HCP, Par, Score, Net, then Putts, Fairways, GIR, Bunkers,
Chips, Penalties, with an Out/In total column. A blank cell means not entered
→
null, never 0. - Fairway icons: ✓ = hit, → = missed right, ← = missed left; blank on a par 3
=
na. The Out/In fairway total (e.g. 3/5) counts only tracked driving holes. - GIR icons: ✓ = green hit; an arrow (↑ ↓ ← →) = missed that way (still a miss). If the per-hole card and the Statistics dial disagree, trust the card (this round: card 1/18 vs dial 8%).
- Statistics → Scores gives bogey/double/worse counts and par-type averages — use them to cross-check the per-hole read, not as the source.
- The 0.0% trap: Scrambling / Up-and-Down / Sand save at 0.0% with no
hole-level chip/bunker data means not tracked → coverage
none, not a real 0.
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 · 100 lines · 86 tokens per session scan A c081a10c6b6d
gamebook-screenshot-analysis is a skill published in the GitHub repository bjornj12/golf-coach (1 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,386 once invoked, about $0.0004 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
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
robosuite/training-law/SKILL
Master reference for ASPIRE Robosuite experiments. Covers system overview, 7 tasks, setup, running experiments, debugging, full API reference, and all pipeline modes (Fix Loop, Baseline).
systemic-emergent-design
Use when designing, auditing, or generating the systemic substrate of a game — the small set of consistent, interacting rules (a "chemistry engine") that produce emergent play, rather than scripted set-pieces. Covers immersive-sim principles (intention & perceivable consequence), multiplicative vs. additive design…
metashape-reconstruction
Guide dense reconstruction, mesh building, and texturing in Metashape MCP. Covers depth maps, point cloud, mesh, texture, DEM, and orthomosaic generation with correct GPU/CPU settings and quality parameters. Works through the Metashape MCP server.
digital-twin-builder
Enriches a Universal Assembly Graph (UAG, produced by the game-designer skill) with simulation-grade semantics -- physical units, material/mass properties, and physics/logic constraints -- so it is ready for a physically meaningful digital twin, not just a visual scene. Use this skill whenever the user wants a UAG to…