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/agentcomputerai/torch/airbnbnpx skills add AgentComputerAI/torch --skill airbnbgit clone --depth 1 https://github.com/AgentComputerAI/torchWhat 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 | $0.00121 | $0.02688 |
| Opus 5 | $0.00060 | $0.01344 |
| Sonnet 5 | $0.00024 | $0.00538 |
| Haiku 4.5 | $0.00012 | $0.00269 |
Grade A, and why
airbnb 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 2d 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.
`curl -sL` returns 200 immediately. No challenge, no JS check, no cookies needed beyond what the response sets. How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airbnb (airbnb.com)
Airbnb's search results page renders fully on the server and ships all listing data inline as JSON. There is no anti-bot wall on
/s/<location>/homes— a singlefetchwith a normal browser User-Agent returns HTTP 200 + ~900KB of HTML containing every listing on the page. Pagination is a flat list of opaque cursors discoverable from page 1.
Detection
| Signal | Value |
|---|---|
| CDN | Akamai (akamai-request-bc header) |
| Origin | nginx, x-instrumentation: airbnb |
| Framework | Custom Airbnb "Niobe" GraphQL client + React SSR |
| Anti-bot | None on /s/ HTML (Arkose Labs only on POST flows) |
| Auth | Not required for search |
| robots.txt | Allows /s/ for major UAs |
curl -sL returns 200 immediately. No challenge, no JS check, no cookies needed beyond what the response sets.
Architecture
- React SSR app shell at
/s/:location?/homes/:additionalRefinements?. - Search payload comes from the internal Niobe GraphQL endpoint (
StaysSearchoperation), but the SSR pass already inlines the response in the HTML. There is no need to replay the GraphQL endpoint. - The inlined JSON lives in one of two script tags depending on which render path served the request:
<script id="data-deferred-state-0">— streaming/deferred render. This is what plainfetchfrom Node usually gets. Path to listings:niobeClientData[0][1].data.presentation.staysSearch.results.searchResults.<script id="data-injector-instances">— fully inlined render (sometimes served tocurl/cached). Path to listings:root[3][1][2][1].data.presentation.staysSearch.results.searchResults.
- Both paths land at the same
presentation.staysSearch.resultsshape, so a stack-based walk that looks foro.staysSearch.results.searchResultsworks on either. - Each page returns 18 results in
searchResults. The map carousel (mapResults.mapSearchResults, ~20) overlaps but isn't needed. - Pagination is a flat list of base64 cursors at
staysSearch.results.paginationInfo.pageCursors(typically 15 cursors → ~270 listings cap per query). Append?cursor=<urlencoded base64>to the same URL.
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.
- 2d ago First seen · 172 lines · 121 tokens per session scan A a24023354652
airbnb is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 121 tokens to every session and 2,688 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
tiny-web-crawler
Crawl from one or more starting web pages, fetch readable content, search within pages, follow relevant links, and stop when the requested information is found or a bounded limit is reached.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browserstack
../../../engineering-team/playwright-pro/skills/browserstack/SKILL.md.
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…