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/arcededev/air-sdk/openai-skillnpx skills add ArcedeDev/air-sdk --skill openai-skillgit clone --depth 1 https://github.com/ArcedeDev/air-sdkWrote 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/arcededev/air-sdk/openai-skill)<a href="https://agentmods.dev/skills/arcededev/air-sdk/openai-skill"><img src="https://agentmods.dev/badge/skills/arcededev/air-sdk/openai-skill.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 | $0.00055 | $0.01078 |
| Opus 5 | $0.00028 | $0.00539 |
| Sonnet 5 | $0.00011 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
air-sdk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIR SDK — Web Intelligence Skill
Use this skill whenever you need to interact with a website or extract data from a URL. AIR gives you collective knowledge from thousands of agents about what works on each site.
Finding the Skill Directory
OpenAI mounts skills at a path like /home/oai/skills/air-sdk-<version>/. To locate it reliably:
SKILL_DIR=$(dirname "$(find /home/oai/skills /mnt/skills -name 'air.js' 2>/dev/null | head -1)")
Use $SKILL_DIR in all commands below. If that doesn't work, try ls /home/oai/skills/ to find the exact path.
Setup
Run once per container:
bash "$SKILL_DIR/setup.sh"
Available Commands
All commands require $AIR_API_KEY (injected via domain_secrets). Output is JSON.
1. Browse Capabilities
Discover what actions are possible on a website before navigating:
node "$SKILL_DIR/air.js" browse amazon.com
Returns: capabilities, confidence scores, execution tiers, available macros, CSS selectors.
2. Extract Structured Data
Extract title, description, content items, and metadata from any URL:
node "$SKILL_DIR/air.js" extract "https://example.com/page"
Best results on: JSON-LD sites, RSS/Atom feeds, JSON APIs, SPAs (YouTube, Next.js). Limited results on retail sites and CAPTCHA-protected pages — use Playwright for those and report what you find.
3. Execute a Capability
Get a step-by-step execution plan with CSS selectors:
node "$SKILL_DIR/air.js" execute kayak.com search_flights '{"origin":"NYC","destination":"Tokyo","date":"2026-04-15"}'
Returns: entry URL, CSS selectors, fallback selectors, execution tier. Use these with Playwright or Puppeteer.
4. Report Outcome
After executing, report what happened so the network learns:
node "$SKILL_DIR/air.js" report kayak.com search_flights true '[{"action":"click","selector":"#search-btn","success":true},{"action":"fill","selector":"input#origin","value":"NYC","success":true}]'
You MUST include the actual CSS selectors you used. Reports without selectors are discarded.
What ships with it
6 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.
- 5d ago First seen · 112 lines · 55 tokens per session scan A 77a238300560
air-sdk is a skill published in the GitHub repository ArcedeDev/air-sdk (1 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,078 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 2026-08-31.
Other skills, from other repositories
browser-automation-expert
Drive a real browser to navigate, extract data and complete flows on sites without an API: scraping, crawling, authentication, dynamic content and anti-bot handling. Use when the user mentions web scraping, crawling, browser automation, Puppeteer or headless Chrome, wants data pulled from a website, needs a login or…
apitap
ApiTap gives AI agents cheap access to web data through three layers.
fortress-stealth-browser
Use when a web fetch is blocked — Cloudflare, DataDome, PerimeterX, Akamai, a 403/429, a CAPTCHA/"Press & Hold", "Access denied", an empty JavaScript shell, or a page whose data only appears after client-side rendering. Drives a real recompiled-Chromium stealth engine (Fortress) via the Fortress MCP to fetch, extract…
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
cookie-debugging
Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party…
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.