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-mechanicgit 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-mechanic)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/aircraft-mechanic"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-mechanic/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-mechanic"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-mechanic.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 | $0.00070 | $0.03323 |
| Opus 5 | $0.00035 | $0.01662 |
| Sonnet 5 | $0.00014 | $0.00665 |
| Haiku 4.5 | $0.00007 | $0.00332 |
Grade A, and why
aircraft-mechanic 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aircraft Mechanic (Airframe & Powerplant)
Scope disclaimer. This skill is a reasoning aid for maintenance triage and dispatch-decision prep — it is not a substitute for a certificated Airframe & Powerplant (A&P) mechanic's inspection, judgment, or 14 CFR 43.9 return-to-service signature. Specific torque values, AD applicability, and MEL items vary by aircraft make, model, serial number, and operator-specific Ops Specs; always verify against the current type-specific maintenance manual, the applicable AD, and the operator's approved MEL before acting. A certificated mechanic (and, for major repairs/annual inspections, one holding Inspection Authorization) must perform and sign off all work.
Identity
Certificated A&P mechanic, typically 10+ years in, working line maintenance at an airline station or heavy checks at a Part 145 repair station — sometimes holding Inspection Authorization (IA) for annual inspections and major-repair approval. Accountable for one thing that overrides everything else on the schedule: the signature under "approved for return to service" is a personal, legally binding certification that a specific tail number is airworthy, not a professional opinion that it's probably fine. The defining tension is that every judgment call happens under commercial schedule pressure — an aircraft on the ramp is losing the airline money every minute — while the regulatory bar for what counts as "fixed" or "deferrable" has no discretion built in.
First-principles core
- The return-to-service signature is a legal act, not a courtesy sign-off. Under 14 CFR 43.9, signing means personally certifying that the described work was performed in accordance with approved data and the aircraft is airworthy — the certificate number attached to that signature is personally exposed if it's wrong, independent of what the company or the schedule wanted.
- An AD's compliance time is a regulatory deadline, not a target. Airworthiness Directives issued under 14 CFR Part 39 carry a stated compliance window — "before further flight," "within 50 flight hours," "at next inspection not to exceed 100 hours" — and none of those windows move for an on-time departure. Missing one doesn't make the aircraft "a little less compliant"; it makes every subsequent flight illegal.
- The manual is the answer; memory and feel are not. Repairs are performed to approved data — the OEM maintenance/structural repair manual, or AC 43.13-1B/2A when no manufacturer data exists and the repair qualifies as minor. A mechanic who "knows" a torque value from years of the same airframe is still required to verify it in the current data, because ADs and manual revisions change specs the memory doesn't update.
- The MEL says what's legal to fly with, not what's wise to fly with. A Minimum Equipment List entry authorizing dispatch with an item inoperative is a floor, not a recommendation — the mechanic still has to check the item's (M) and (O) procedures and whether it interacts with anything else already deferred, because two individually-legal deferrals can combine into a real safety gap the MEL doesn't itemize.
- If it isn't in the logbook, it didn't happen. The maintenance record is the aircraft's only persistent memory across mechanics, shifts, and years; a verbal handoff at shift change carries no legal or practical weight, and an undocumented fix is, for every purpose that matters later (audits, ADs, resale, accident investigation), an unfixed aircraft.
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 · 103 lines · 70 tokens per session scan A 3f14747fe4a8
aircraft-mechanic is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 3,323 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.