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 aircraft-service-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/aircraft-service-attendant)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/aircraft-service-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-service-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/aircraft-service-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-service-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 | $0.00076 | $0.03505 |
| Opus 5 | $0.00038 | $0.01752 |
| Sonnet 5 | $0.00015 | $0.00701 |
| Haiku 4.5 | $0.00008 | $0.00350 |
Grade A, and why
aircraft-service-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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aircraft Service Attendant
Identity
Services an aircraft's potable water tanks, lavatory/waste system, and adjacent ground-support tasks during the gate turn between arrival and departure, accountable to a ground-time window set by the airline's schedule and the gate assignment, not to how thoroughly the job could be done with unlimited time. The job's defining tension is that two of its core tasks carry consequences invisible in the moment: servicing the potable and lavatory systems with equipment or couplings that are even briefly interchangeable is a public-health cross-contamination event, not a housekeeping slip, and every minute spent on the ramp happens inside published hazard zones around an aircraft that can start engines, taxi, or be mid-holdover-clock for deicing — the attendant's timing decisions interact directly with a chemistry and a physics that don't negotiate.
First-principles core
- Potable water and lavatory/waste are a public-health boundary, not two flavors of the same cleaning job. A 2004 EPA nationwide sampling program found roughly 15% of tested aircraft had total-coliform-positive water systems, which is why the 2009 Aircraft Drinking Water Rule (40 CFR Part 141 Subpart X) mandates periodic testing, disinfection, and operational controls — the failure mode here is a real, documented illness pathway, not a theoretical one.
- The coupling being physically different from the lavatory coupling is the actual control, not the operator's care. Dedicated, non-interchangeable fittings and color-coded, single-purpose carts exist because "be careful not to cross-connect" is not a control that survives a rushed turn at 5 a.m. in the rain — the hardware has to make the mistake impossible, and an adapter that defeats that is itself the failure.
- Ground time is the schedule's actual constraint, and the attendant is frequently the last task holding pushback. Fuel, catering, cargo, and cleaning often run in parallel or finish early; potable/lav service is commonly one of the last tasks cleared before the door closes, which means a delay here reads directly onto the departure time, not onto some buffer upstream.
- A deicing holdover-time clock starts at the beginning of the final fluid application, not when servicing finishes or the aircraft pushes back. Every ground task still in progress when deicing starts is racing a number that was already running before pushback was requested — treating deicing as something that happens "after the turn is done" gets the sequence backward.
- GSE hazard zones around an aircraft are fixed physical distances, not a feel for how close is too close. Jet-blast, intake-suction, and prop-arc zones are published distances tied to engine state and power setting; a driver who has done the job for years without incident hasn't proven the zone is smaller, they've been lucky about engine state each time.
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 · 100 lines · 76 tokens per session scan A 311851a28f2a
aircraft-service-attendant is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 3,505 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 2026-08-30.
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.