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 producthuntgit 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/producthunt)<a href="https://agentmods.dev/skills/agentcomputerai/torch/producthunt"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/producthunt/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/producthunt"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/producthunt.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 | $0.00111 | $0.01987 |
| Opus 5.5 | $0.00044 | $0.00795 |
| Sonnet 5.5 | $0.00022 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
producthunt 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.
| Anti-bot | Cloudflare managed challenge on bare curl → HTTP 403 | How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Hunt (producthunt.com)
Cloudflare-gated homepage that renders the full daily/weekly/monthly leaderboard directly into HTML. No JSON blob, no API replay — just cheerio over the DOM after a real-Chrome navigation.
Detection
| Signal | Value |
|---|---|
| CDN | Cloudflare (cf-ray, cf-mitigated: challenge) |
| Framework | Custom React SSR (no __NEXT_DATA__, no __APOLLO_STATE__) |
| Anti-bot | Cloudflare managed challenge on bare curl → HTTP 403 |
| Auth | None required for homepage |
| robots.txt | Allows / |
Bare curl https://www.producthunt.com/ → HTTP/2 403 with cf-mitigated: challenge. A puppeteer.connect to the user's real Chrome (127.0.0.1:9222) clears the challenge in <1s with zero intervention — no stealth plugin, no proxy, no captcha solver.
Architecture
Homepage is server-rendered HTML (~2.3 MB). All 92 posts for the current window are in the initial response under four sibling containers:
[data-test="homepage-section-today"]— ~74 posts[data-test="homepage-section-yesterday"]— top 6[data-test="homepage-section-last-week"]— top 6[data-test="homepage-section-last-month"]— top 6
Each post is a <section data-test="post-item-<id>"> block.
Strategy used
- Phase 0 (curl): blocked by Cloudflare (
cf-mitigated: challenge, 403). - Phase 1 (framework JSON): no
__NEXT_DATA__, nowindow.__APOLLO_STATE__. Skipped. - Phase 2 (browser):
puppeteer.connect({ browserURL: "http://127.0.0.1:9222" })→ challenge clears instantly, HTML contains everything. Done.
Stealth config that works
None. Just connect to real Chrome:
const browser = await puppeteer.connect({
browserURL: "http://127.0.0.1:9222",
});
const page = await browser.newPage();
await page.goto("https://www.producthunt.com/", { waitUntil: "domcontentloaded" });
// Optional: poll title until it's not "Just a moment..."
await page.waitForSelector('section[data-test^="post-item-"]', { timeout: 15000 });
On teardown use browser.disconnect() — never browser.close() (would kill the user's real Chrome).
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 · 163 lines · 111 tokens per session scan A 464aa211d5d3
producthunt is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 111 tokens to every session and 1,987 once invoked, about $0.0004 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.