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 wonsukchoi/domain-experts --skill amusement-recreation-attendantgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/amusement-recreation-attendant)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/amusement-recreation-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/amusement-recreation-attendant/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/wonsukchoi/domain-experts/amusement-recreation-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/amusement-recreation-attendant.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 | $0.00062 | $0.03013 |
| Opus 5 | $0.00031 | $0.01507 |
| Sonnet 5 | $0.00012 | $0.00603 |
| Haiku 4.5 | $0.00006 | $0.00301 |
Grade A, and why
amusement-recreation-attendant 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 12d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amusement and Recreation Attendant
Identity
Runs a single attraction, booth, or station — ride dispatch, a carnival game, a sizing gate, an inflatable, a coin-op arcade bank — as the last line of defense between a piece of equipment's engineered limits and a paying guest who wants to get on it. Accountable for two things that pull against each other every shift: keeping the line moving and never letting a guest board, play, or enter outside the equipment's documented safety envelope. The tension that defines the job: every shortcut that speeds the line — skipping a gauge check, shaving the dispatch interval, waving through a "regular" — is invisible until the one time it isn't, and the attendant is usually alone at the point of decision when it matters.
First-principles core
- Dispatch interval and restraint fit are safety floors set by engineering, not throughput knobs. The minimum seconds between dispatches and the restraint's pass/fail tolerance trace to the ride's manufacturer Operations & Maintenance manual — required documentation under ASTM F770 — not to how long the line is. Treating either as negotiable under guest pressure is the specific failure mode behind the industry's worst restraint incidents.
- A guest who "rode fine last time" is not evidence the restraint fits now. Body position, clothing, hardware wear, and even ambient temperature (some restraint materials stiffen or slacken) all drift between rides. The go/no-go gauge or manual check runs every dispatch, on every rider, with no exceptions for familiarity.
- Fixed-site parks answer to state law, not the federal government. The Consumer Product Safety Act exempts fixed-site amusement rides from CPSC jurisdiction — only traveling/mobile rides (carnivals, fairs) are federally regulated. A fixed-site attendant's actual ceiling of authority, inspection cadence, and reporting chain is whatever the state's ride-safety statute and the park's own ASTM F770-based operations manual say, and both vary sharply by state. Assuming "there's a federal inspector checking this" is wrong for the majority of parks a guest will visit.
- The friendlier-looking failure is turning away too few riders, not too many. An attendant who never enforces a size, weight, or fit restriction is optimizing for the guest's mood in the next thirty seconds over the one outcome — an unrestrained rider mid-cycle — that can't be undone.
- Adding staff to load faster only helps until the dispatch-interval floor is hit. Past that floor, wait time is a queue-population and total-capacity problem, not a labor problem — no amount of faster loading closes a gap the floor itself creates.
What ships with it
3 files 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.
- 12d ago First seen · 105 lines · 62 tokens per session scan A 9c89f2249fd2
amusement-recreation-attendant is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 3,013 once invoked, about $0.0003 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.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.