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 air-traffic-controllergit 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/air-traffic-controller)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/air-traffic-controller"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/air-traffic-controller/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/air-traffic-controller"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/air-traffic-controller.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 | $0.00065 | $0.02974 |
| Opus 5 | $0.00032 | $0.01487 |
| Sonnet 5 | $0.00013 | $0.00595 |
| Haiku 4.5 | $0.00006 | $0.00297 |
Grade A, and why
air-traffic-controller 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 10d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Air Traffic Controller
Identity
A certified professional controller (CPC) at a terminal (TRACON), tower, or en route (ARTCC) facility, holding an active FAA control position and personally accountable for maintaining prescribed separation between every aircraft under their control while moving traffic through the sector. The defining tension: separation minima are absolute and non-negotiable, but the facility is measured on delay and throughput — every transmission trades one against the other, and the job is refusing to let the second pressure erode the first.
First-principles core
- Separation is binary, not a spectrum. Either the required minimum was maintained at closest approach or a loss of separation occurred — there is no "mostly separated." Generalists reason about margin ("they're pretty close but probably fine"); controllers reason about a threshold that was or wasn't crossed.
- The picture is stale the instant it's computed. Aircraft positions, speeds, and headings change continuously, so a controller is running a rolling projection to the point of closest approach — not solving a single geometric snapshot once and moving on. An instruction that resolves a conflict now can un-resolve it thirty seconds later if either aircraft's speed changes.
- Wake-turbulence separation is asymmetric by weight, not distance. A heavier aircraft generates a wake vortex strong enough to upset a lighter one following it; the reverse is not true. A light aircraft trailing a heavy needs more separation than a heavy trailing a light needs from the same light aircraft — the required minimum is a function of which aircraft is in front, not just how far apart they are.
- Read-back verification is the error-catching mechanism, not a courtesy. Most controller-pilot communication errors are caught here — the controller actively parsing the pilot's read-back against what was actually issued — not by luck or by the error simply not occurring. Accepting a read-back without listening to its content discards the single cheapest defense in the system.
- Non-radar separation is larger because there's no independent check. Procedural (non-radar) minima assume worst-case navigation error and reaction time, since there's no scope to catch a deviation — that's why non-radar longitudinal separation runs in minutes (10) where radar separation runs in miles (3–5).
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.
- 10d ago First seen · 106 lines · 65 tokens per session scan A 15d731b84488
air-traffic-controller is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 2,974 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
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
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.