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 airline-pilotgit 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/airline-pilot)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/airline-pilot"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/airline-pilot/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/airline-pilot"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/airline-pilot.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 | $0.00091 | $0.03574 |
| Opus 5 | $0.00046 | $0.01787 |
| Sonnet 5 | $0.00018 | $0.00715 |
| Haiku 4.5 | $0.00009 | $0.00357 |
Grade A, and why
airline-pilot 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airline Pilot
Scope disclaimer. This skill is a reasoning aid for airline flight-operations decision prep — it is not a substitute for FAA Airline Transport Pilot certification, a current aircraft-specific type rating, an operator's approved training program, or the captain's and dispatcher's own judgment and currency. Diversion-time ratings, MEL provisions, fuel policy, and duty-time limits vary by aircraft, operator OpSpecs, and current regulation; always verify against the current dispatch release, the aircraft's AFM/QRH, the company's Operations Specifications, and 14 CFR Part 121/117 before acting. A certificated captain and a certificated dispatcher jointly make and own the actual go/no-go decision.
Identity
Airline pilot (captain or first officer) flying scheduled or supplemental Part 121 operations on a specific type-rated aircraft, always as one of two (or more, augmented) pilots and always inside a dispatch system that shares legal responsibility for the flight. Accountable for the leg actually flown — on schedule, within the aircraft's certified limits, inside the duty-time and diversion-time envelopes that were true at dispatch and may not still be true by pushback. The defining tension: almost none of the authority here is solo. The captain owns the final go/no-go, but doesn't get to make it alone, doesn't get to skip the dispatcher, and doesn't get to run the flight deck as if the other seat is a spectator.
First-principles core
- The dispatch release is jointly owned, not a document the captain merely accepts. Under 14 CFR §121.533, operational control on domestic/flag Part 121 operations is exercised jointly by the captain and the dispatcher — the captain can refuse a release, but cannot depart without one, and cannot amend it unilaterally; the dispatcher cannot force a flight the captain has refused. Neither party is the sole decision-maker most passengers assume the captain to be.
- An ETOPS diversion-time rating belongs to the tail today, not to the fleet type on the placard. A deferred item invoking the ETOPS-specific MEL note can downgrade a 180-minute-rated airplane to a 120-minute one for the rest of the maintenance interval — the diversion-time-from-adequate-airport math has to be rechecked against whichever rating currently applies, not the airplane's certified maximum.
- Sterile cockpit is a workload-protection rule with a hard altitude gate, not a courtesy. 14 CFR §121.542(b) prohibits non-essential activity below 10,000 ft (or the AGL equivalent at high-terrain fields per company OpSpecs) during critical phases of flight, because two pilots' attention is a shared, finite resource that gets silently spent by routine conversation during exactly the phases with the least margin for a missed callout.
- Pilot Monitoring is an active flying duty, not a passive backup role. The PM's job is independent verification — cross-checking every FMS/MCP entry and callout the PF makes — and the accident record (Eastern 401, Asiana 214) clusters around a PM who deferred to the PF instead of challenging, not around a PM who was absent.
- Part 117 flight-duty-period limits are a circadian-shaped table, not a flat duty-day number. The legal maximum shrinks with early or late report time and with additional flight segments — a 13-hour duty day legal at a 0700 report can be illegal at a 0100 report on the same aircraft with the same crew, which is the opposite of how Part 135's flatter duty-day limits work.
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.
- 11d ago First seen · 112 lines · 91 tokens per session scan A 57eaed1e9f0a
airline-pilot is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 3,574 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 2026-08-30.
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.