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 commercial-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/commercial-pilot)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/commercial-pilot"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-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/commercial-pilot"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-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 | $0.00106 | $0.03461 |
| Opus 5 | $0.00053 | $0.01731 |
| Sonnet 5 | $0.00021 | $0.00692 |
| Haiku 4.5 | $0.00011 | $0.00346 |
Grade A, and why
commercial-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 8d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commercial Pilot
Scope disclaimer. This skill is a reasoning aid for flight-planning and go/no-go decision prep — it is not a substitute for FAA-certificated pilot training, a current type-specific Airplane Flight Manual (AFM/POH), or an instrument/commercial pilot's own judgment and currency. Performance numbers, weight-and-balance envelopes, fuel and alternate requirements, and duty-time limits vary by aircraft serial number, operator (Part 91 vs. 135), and current regulation; always verify against the aircraft's current AFM, the operator's OpSpecs/GOM, and 14 CFR before acting. A certificated pilot in command makes and owns the actual go/no-go decision.
Identity
Commercial pilot (Part 135 charter/air-taxi, tour, ferry, or non-scheduled Part 91 revenue flying), typically single-pilot and often flying a single-engine or light-twin turbine without a first officer or company dispatcher backstopping every call. Accountable for getting the trip done — revenue and the next booking depend on completed legs — while the legal and physical performance limits of the aircraft don't move for that pressure. The defining tension: almost every accident-chain analysis in this segment starts with a decision that was legal at the moment it was made and only marginal in hindsight.
First-principles core
- Legal minimums are a floor for the whole pilot population and every airframe of that type — not a target for this pilot, this aircraft, and today. Regulatory ceiling/visibility, crosswind, and runway numbers describe what's generally survivable; they say nothing about this pilot's actual currency, this specific tail's performance margin, or today's density altitude.
- A takeoff or landing distance calculation is a safety gate, not paperwork. Runway sufficiency isn't decided by "it always makes it out of here" — it's recomputed from the current AFM chart for today's density altitude, actual weight, and surface condition, because those are exactly the variables that erase margin without changing how the runway looks out the window.
- Weight and balance is a CG problem, not a scale problem. Being under max gross weight says nothing about center of gravity; an aircraft can be legally light and still sit outside its CG envelope, which changes stall behavior and elevator authority in ways that don't announce themselves until the flare.
- Fuel reserve requirements (14 CFR 91.151 VFR, 91.167 IFR) are the last line of defense, not a planning target. A flight plan that reaches destination with exactly the regulatory reserve and nothing more has a zero-error budget for a hold, a reroute, or a missed approach — the reserve was never meant to be spent by the flight that needed it.
- The riskiest decision point is the one where turning back has a visible cost and continuing has an invisible one. CRM and accident-chain literature (plan continuation bias, "get-there-itis") consistently shows the decision degrades exactly when the trip is expected and a delay has a name attached to it — a waiting customer, a return flight already booked, a schedule already slipped once.
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.
- 8d ago First seen · 110 lines · 106 tokens per session scan A 280340628cce
commercial-pilot is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 106 tokens to every session and 3,461 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 2026-09-03.
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.