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/doordashnpx skills add AgentComputerAI/torch --skill doordashgit 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 | $0.00082 | $0.01977 |
| Opus 5 | $0.00041 | $0.00988 |
| Sonnet 5 | $0.00016 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
doordash 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.
| **CDN** | Cloudflare (`cf-ray`, `cf-mitigated`, "Just a moment..." on raw curl) | How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DoorDash (doordash.com)
React SPA served through Cloudflare. Deal pages are server-side rendered with all items inlined in the initial HTML — don't bother with the GraphQL endpoints. A headed stealth Puppeteer session clears the Cloudflare challenge automatically; no captcha solver or proxy needed.
Detection
| Signal | Value |
|---|---|
| CDN | Cloudflare (cf-ray, cf-mitigated, "Just a moment..." on raw curl) |
| Framework | React SPA with SSR bootstrap |
| Anti-bot | Cloudflare Managed Challenge — clears via stealth plugin, no CAPTCHA |
| Rendering | SSR for deals carousels; GraphQL for personalized/auth surfaces |
| Auth | Not required for /browse/deals |
| Geo | Results vary by geoIP — default US egress lands in SF 94107 |
Strategy
Puppeteer (stealth, headed)
→ wait for networkidle2
→ scroll to trigger lazy sections
→ parse rendered HTML with Cheerio
Do NOT hit the GraphQL endpoints:
/graphql/homeLandingPageStores,getGeoByIP, etc. fire on page load but none return the deals feed.- The typical
facetFeedendpoint only fires on authenticated/personalized surfaces, not/browse/deals. - The deals feed is inlined in the SSR HTML — parse that directly.
Stealth config that works
import puppeteer from "puppeteer-extra";
import StealthPlugin from "puppeteer-extra-plugin-stealth";
puppeteer.use(StealthPlugin());
const browser = await puppeteer.launch({
headless: false,
args: [
"--no-sandbox",
"--disable-setuid-sandbox",
"--disable-blink-features=AutomationControlled",
],
});
const page = await browser.newPage();
await page.goto("https://www.doordash.com/browse/deals", { waitUntil: "networkidle2" });
Standard Chrome UA is fine — no rotation needed. Cloudflare clears on its own once JS runs.
Verify you're past the challenge before parsing:
const title = await page.title();
if (title !== "Deals | Doordash") {
throw new Error(`Unexpected page title: ${title} — Cloudflare may still be challenging`);
}
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 · 201 lines · 82 tokens per session scan A 95368a0c1474
doordash is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,977 once invoked, about $0.0004 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.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
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…