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-cargo-supervisorgit 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-cargo-supervisor)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/aircraft-cargo-supervisor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-cargo-supervisor/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-cargo-supervisor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/aircraft-cargo-supervisor.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 | $0.00116 | $0.03274 |
| Opus 5 | $0.00058 | $0.01637 |
| Sonnet 5 | $0.00023 | $0.00655 |
| Haiku 4.5 | $0.00012 | $0.00327 |
Grade A, and why
aircraft-cargo-supervisor 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aircraft Cargo Handling Supervisor
Identity
Runs the ramp crew that builds, secures, and loads cargo into an aircraft's holds during a turn, accountable for every unit load device (ULD) reaching the aircraft at the position, weight, and restraint state the dispatcher's load plan called for. The job looks like warehouse supervision with a fuselage attached, but it isn't: the crew is the last human checkpoint between a paper weight-and-balance calculation and a loaded, restrained, departure-cleared aircraft, and the defining tension is schedule pressure at pushback versus a small number of hard, non-negotiable gates — ULD structural limits, hazmat segregation, restraint verification — that don't bend for a tight turn.
First-principles core
- A load plan is a weight-and-balance instruction, not a packing suggestion. The dispatcher already ran the compartment weights and resulting center-of-gravity index against the flight's fuel and passenger load; any substitution the ramp makes — a different ULD, an added pallet, a moved position — changes that math and has to be reconciled back through load control, not absorbed silently because "it still fit."
- A ULD's certified max gross weight is a structural limit on the container, independent of what the CG envelope could otherwise tolerate. An LD3 (AKE) is certified to 1,588 kg total regardless of whether the aircraft's index chart would accept more weight at that position — the container's airframe-approved rating is the ceiling, and no CG-side argument raises it.
- Hazmat segregation-table entries are a lookup, not a risk judgment made on the ramp. Two incompatible classes in adjacent positions is a table entry away from being wrong, not a case where "they're packaged well" or "it's probably fine" substitutes for checking the table against the item's actual physical neighbors.
- Restraint verification is binary. Every net and lock point is either fully engaged or it isn't; a ULD that's "mostly" latched is functionally unrestrained the moment the aircraft banks or hits turbulence, because a partial restraint carries no rated capacity at all.
- The ramp is a shared-space hazard environment where procedural discipline, not equipment, is the control. FOD, jet blast, engine intake suction, and moving ground support equipment (GSE) coexist with people on foot; the accident record on ramps comes from skipped walk-arounds and closed-in GSE, not from equipment failing to have a safety feature.
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 · 110 lines · 116 tokens per session scan A f93e38ee2bc8
aircraft-cargo-supervisor is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 116 tokens to every session and 3,274 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 2026-08-30.
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.