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 AgentComputerAI/torch --skill ebaygit clone --depth 1 https://github.com/AgentComputerAI/torchWrote 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/agentcomputerai/torch/ebay)<a href="https://agentmods.dev/skills/agentcomputerai/torch/ebay"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/ebay/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/agentcomputerai/torch/ebay"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/ebay.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 | $0.00078 | $0.01893 |
| Opus 5.5 | $0.00031 | $0.00757 |
| Sonnet 5.5 | $0.00016 | $0.00379 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
ebay 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 1mo 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.
- **Phase 0 (curl)** — blocked by splash challenge (`Pardon Our Interruption`). Skipped Phase 1. How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eBay (ebay.com)
eBay search pages are server-rendered HTML behind a one-time JS splash challenge (
splashui/challenge, "Pardon Our Interruption"). Withpuppeteer.connect()to the user's real Chrome the challenge auto-redirects in under a second and theul.srp-resultslist is fully populated. No captcha, no proxies.
Detection
| Signal | Value |
|---|---|
| Server | ebay-proxy-server |
| Challenge | 307 → /splashui/challenge?ap=1&appName=orch&ru=... (title: "Pardon Our Interruption...") |
| Framework | Marko-rendered SSR HTML + eBay RUM client JS |
| Anti-bot | Custom splash challenge (uzm* cookies, _crefId JOSE token) — clears on real Chrome automatically |
| Auth | Not required for search |
| robots.txt | /sch/ allowed for anonymous crawling |
Architecture
- URL template:
https://www.ebay.com/sch/i.html?_nkw=<query> - First anonymous hit returns 307 → splash challenge HTML; the JS on that page sets
__uzm*cookies, POSTs a token, and redirects back to the original URL. - Once cookies are set (which happens instantly in a real Chrome profile) the SRP is plain SSR HTML. All items are present on load — no infinite scroll — but images/below-the-fold cards are lazy-loaded, so scroll before extracting.
- Listing cards are
<li class="s-card">insideul.srp-results. Newer layout — the legacy.s-itemselectors no longer exist on /sch/i.html (2026).
Strategy used
- Phase 0 (curl) — blocked by splash challenge (
Pardon Our Interruption). Skipped Phase 1. - Phase 2 (browser) —
puppeteer.connect({ browserURL: "http://127.0.0.1:9222" })cleared the challenge in one redirect. Extraction is pure DOM scraping; no API replay needed.
Stealth config that works
No stealth plugin needed when using the real Chrome profile. Minimal connect:
const browser = await puppeteer.connect({ browserURL: "http://127.0.0.1:9222" });
const page = await browser.newPage();
await page.setViewport({ width: 1400, height: 900 });
await page.goto(url, { waitUntil: "domcontentloaded", timeout: 45000 });
// If first hit landed on the splash page, wait for the auto-redirect
if ((await page.title()).includes("Pardon")) {
await page.waitForNavigation({ timeout: 30000 }).catch(() => {});
}
await page.waitForSelector("ul.srp-results > li.s-card", { timeout: 30000 });
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.
- 1mo ago First seen · 152 lines · 78 tokens per session scan A ed6f12543b4b
ebay is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 78 tokens to every session and 1,893 once invoked, about $0.0003 per session on Opus 5.5. 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
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
data-scraper
Use when data lives on a website with no usable API — listings, prices, public records — and the scrape must stay legal and not get blocked: legal gate, extraction path, durable selectors, pacing, resilience. NOT parsing bytes you already hold into fields (that is structured-extraction), NOT a documented API or key…
nodejs
Use when building or operating a plain Node.js / Express 5 backend service: project layout, async correctness, central error middleware, fail-fast config, graceful shutdown on SIGTERM. NOT DI modules/providers/guards (that is nestjs), NOT the type system or tsconfig (that is typescript), NOT REST contract design (that…
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
browser-automation
A browser-automation workflow that detects the terminal environment and chooses a browser control tool. It supports opening pages, taking snapshots, clicking, filling fields, and other checks.