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 agentmods add skills/deepskyai/agent-tools/aviation-regulationsnpx skills add deepskyai/agent-tools --skill aviation-regulationsgit clone --depth 1 https://github.com/deepskyai/agent-toolsWrote 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/deepskyai/agent-tools/aviation-regulations)<a href="https://agentmods.dev/skills/deepskyai/agent-tools/aviation-regulations"><img src="https://agentmods.dev/badge/skills/deepskyai/agent-tools/aviation-regulations.svg" alt="Measured on agentmods" 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 | $0.00129 | $0.01706 |
| Opus 5 | $0.00064 | $0.00853 |
| Sonnet 5 | $0.00026 | $0.00341 |
| Haiku 4.5 | $0.00013 | $0.00171 |
Grade A, and why
aviation-regulations scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`scripts/deepsky_search.py` is a zero-dependency Python CLI (uses only the stdlib). Prefer it over hand-rolled curl because it prints citations in a form easy to quote back to the user. How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aviation Regulations (via Deepsky API)
Deepsky (deepskyai.com) publishes an open, no-auth search API over a curated corpus of aviation regulations and manuals (ICAO, FAA 14 CFR, EASA, CASA) plus supporting advisory material. It also exposes standard agent-discovery endpoints (llms.txt, OpenAPI, plugin manifest, skills registry).
Use this skill whenever an aviation regulatory or operational-doc question comes up, instead of guessing from training data. The corpus is authoritative and multi-jurisdictional; training data often isn't.
Core workflow
- Formulate a natural-language query. Aviation-specific phrasing works best. Include the jurisdiction (FAA, EASA, CASA, ICAO) and the operation type (Part 91, 121, 135, EDTO, IFR, etc.) when known.
- Call
POST /api/v1/search(no auth). Preferscripts/deepsky_search.py— it handles the POST, parses the response, and prints citations. - Cite from
heading_path+metadata. Every match includes a breadcrumb (e.g.14 CFR 135.223) andCountry. Always cite these back to the user. Do not paraphrase without the citation. - Broaden or re-query if needed. If the top hits are off-jurisdiction or off-topic, rephrase (add the specific CFR part, MOS, or ICAO annex), or bump
matchCount(max 20).
Primary endpoint: Search
POST https://www.deepskyai.com/api/v1/search
Content-Type: application/json
{"query": "<natural-language question>", "matchCount": 8}
query(string, required): natural-language search querymatchCount(int, optional, 1–20, default 8): number of matches to return
Response shape:
{
"query": "...",
"count": 8,
"source": "hybrid_search_rpc",
"matches": [
{
"content": "<excerpt from the document>",
"heading_path": "Part 135 > Subpart D > § 135.223 IFR: Alternate airport requirements. > 14 CFR 135.223",
"metadata": {
"Heading Level 1": "...",
"Heading Level 6": "§ 135.223 IFR: Alternate airport requirements.",
"Page Numbers": [71, 72],
"Country": "US"
},
"document_id": null,
"score": null
}
]
}
What ships with it
2 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.
- 6d ago First seen · 135 lines · 129 tokens per session scan A 6317008f9783
aviation-regulations is a skill published in the GitHub repository deepskyai/agent-tools (1 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 1,706 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
find-law-firm
Use whenever the user wants to find, shortlist, vet, or enrich US B2B law firms — corporate, IP/patent, M&A and securities, employment, commercial litigation, regulatory/compliance, data privacy/cyber, real estate, and tax. Triggers on "find three boutique IP law firms in California", "shortlist M&A counsel for a…
never-split-difference
Master FBI hostage negotiation techniques adapted for business. Apply Chris Voss' proven methods to close deals, handle objections, and negotiate from a position of strength. Use when: High-stakes negotiations where outcomes matter significantly; Difficult conversations with clients, vendors, or partners; Price…
nda-generator
Create appropriate non-disclosure agreements for different business contexts with balanced terms and proper scope definitions.
terms-analyzer
Analyze terms of service and privacy policies to identify concerning clauses, hidden permissions, and user rights implications.
resume-screener
Screen resumes efficiently against job requirements with structured scoring, red flag identification, and interview recommendations.
gdpr-compliance
Ensure GDPR compliance for marketing activities including consent management, data processing, privacy notices, and data subject rights.