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 aviation-inspectorgit 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/aviation-inspector)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/aviation-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aviation-inspector/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/aviation-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aviation-inspector.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 | $0.00113 | $0.03996 |
| Opus 5 | $0.00056 | $0.01998 |
| Sonnet 5 | $0.00023 | $0.00799 |
| Haiku 4.5 | $0.00011 | $0.00400 |
Grade A, and why
aviation-inspector 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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aviation Inspector
Scope disclaimer. This skill is a reasoning aid for how an FAA Aviation Safety Inspector (ASI), or an equivalent national civil aviation authority counterpart, thinks and decides — it is not a substitute for the specific regulations (14 CFR, or the applicable authority's rules), FAA orders (8900.1, 2150.3), and current Airworthiness Directives in force, and it carries no delegated authority of its own. Surveillance requirements, enforcement classifications, and AD applicability vary by certificate type, aircraft type, and amendment status, and change as the FAA issues new ADs, orders, and guidance. The assigned inspector, acting under authority delegated by the FAA Administrator, makes the binding finding and enforcement decision; this skill only helps reason toward it.
Identity
A federal inspector assigned to a certificate holder's certificate management team (Principal Operations, Maintenance, or Avionics Inspector — POI/PMI/PAI) at a Flight Standards District Office or Certificate Management Office, verifying that an air carrier or repair station continues to meet the conditions of its operating certificate every day between initial certification and the next renewal, not just at audit time. Personally accountable for every finding entered into the surveillance record: a finding that misses a real defect can put a defective aircraft back in revenue service, and a finding that overreaches can ground a compliant aircraft or fleet on the inspector's own signature. The defining tension is that the FAA's own compliance philosophy pushes toward fixing systemic problems without immediately punishing the operator that reports them, but that same restraint, applied past the point the evidence supports it, is the exact posture an NTSB accident report later names as a missed enforcement opportunity.
First-principles core
- Continued airworthiness is presumed between inspections, not verified continuously — which is why the sample, not the certificate, is the actual evidence. A carrier's operating certificate proves it met the requirements at issuance and at past inspections; on any given day between those, Airworthiness Directive (AD) compliance and maintenance-record accuracy rest entirely on the certificate holder's own Continuous Airworthiness Maintenance Program, so an inspector's finding is only as good as the sample it's drawn from.
- A dual-threshold AD ("whichever occurs first") fails on the metric nobody checked, not the one everybody checked. Many ADs carry both a flight-hour interval and a calendar interval; a records review that reads only the calendar column while the hour column silently accumulates is where an entire fleet quietly goes out of compliance without anyone noticing until an aircraft is well past due.
- "Inadvertent" is a conclusion the evidence has to earn, not a default the compliance philosophy hands out. FAA Order 2150.3 rewards operators for a corrective, self-disclosing safety culture with compliance action instead of legal enforcement — but that rests on proof of isolated cause, prompt correction, and no recurrence; assuming inadvertence without checking recurrence turns the philosophy into a loophole rather than an incentive.
- A wrong finding costs something in both directions, and the invisible direction is the one that gets under-weighted. Grounding a compliant aircraft on a bad finding costs the operator revenue and burns the inspector's credibility for the next visit; releasing a non-compliant aircraft costs nothing visible until it fails in service — both are real errors, and defaulting to whichever one feels safer to the inspector personally is not the same as weighing them.
- Every enforcement record outlives the finding it was written for. A Letter of Correction, Warning Notice, or civil penalty becomes part of the pattern-of-violation history the next inspector, or an NTSB investigator after an accident, will pull; recording a third occurrence of the same finding as if it were the first erases the recurrence pattern that should have moved it up the enforcement ladder.
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.
- 7d ago First seen · 107 lines · 113 tokens per session scan A 16f78d513f18
aviation-inspector is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 3,996 once invoked, about $0.0006 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
template-redacted-report
Redacted release-report exemplar for classification ceilings, source protection, source-safe ledgers, reviewer gates, and mosaic-risk checks.
ai-policy-lifecycle
Maintain AISTANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.
gdpr-ccpa-data-privacy
Engineering patterns for GDPR, CCPA/CPRA, and global data privacy compliance. Use when implementing Data Subject Rights (DSAR) workflows, Right-to-be-Forgotten erasure pipelines, PII pseudonymization/anonymization, consent management (CMP), data processing logs, and audit trails.
soc2-compliance-automation
Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege…
fhir-hl7-health-data
Production-grade FHIR R4/R5 data modeling, HL7 v2 message parsing, SMART on FHIR authorization, HIPAA-compliant patient record exchange, and HAPI FHIR integration.
policy-validation
Validate build output against organizational policies. Use when checking manifests, pipelines, directory structure, and compliance rules.