Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AgentComputerAI/torchnpx agentmods add skills/agentcomputerai/torch/homedepotWrote 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/homedepot)<a href="https://agentmods.dev/skills/agentcomputerai/torch/homedepot"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/homedepot/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/homedepot"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/homedepot.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 | $0.00124 | $0.02359 |
| Opus 5.5 | $0.00050 | $0.00944 |
| Sonnet 5.5 | $0.00025 | $0.00472 |
| Haiku 4.5 | $0.00012 | $0.00236 |
Grade A, and why
homedepot 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.
description: Proven scraping playbook for homedepot.com search results (/s/<query>). Akamai Bot Manager hard-blocks raw curl with HTTP 403 (AkamaiGHost), but a puppeteer connection to the user's real Chrome via the real How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home Depot (homedepot.com)
Akamai-protected Next.js site. Curl is dead on arrival (403 AkamaiGHost). Real Chrome via
127.0.0.1:9222passes silently. Once inside, product data is fully server-rendered in HTML — cheerio parses it. No API replay needed.
Detection
| Signal | Value |
|---|---|
| CDN / WAF | AkamaiGHost + Akamai Bot Manager (bm_ss, bm_so, akavpau) |
| Framework | Next.js (React SSR, #__NEXT_DATA__ present but minimal) |
| Anti-bot | Akamai sensor challenge — 403 on curl, silent pass in real Chrome |
| Auth | Not required for search |
| Store / geo | Prices and stock are localized; uses signed-in store cookie |
Architecture
/s/<query>is an SSR search results page. All 24 product tiles are present in the initial HTML.- Each product tile is rendered twice in the DOM (likely mobile + desktop layout variants). Dedupe by product ID parsed from the
/p/.../<id>href, or by the id itself. Expectpods.length == 48andunique == 24. #__NEXT_DATA__exists but is not needed — direct cheerio selectors on[data-testid="product-pod"]give everything.- No XHR/API replay necessary. No need to scroll, click, or dismiss modals. Just
domcontentloaded+waitForSelector.
Strategy used
- Phase 0 (curl) — fails.
curl -sL https://www.homedepot.com/s/drill→ HTTP 403AkamaiGHost, 2.3KB sensor challenge body. Do not waste time here. - Phase 1 (framework JSON) —
__NEXT_DATA__is present but the searchModel payload is not populated (SSR streams tiles as HTML, not JSON). Skip. - Phase 2 (browser) —
puppeteer.connect({ browserURL: the real Chrome debug port })→page.goto(url, { waitUntil: "domcontentloaded" })→waitForSelector('[data-testid="product-pod"]'). Passes with zero friction. No stealth plugin needed — it IS the user's 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 · 151 lines · 124 tokens per session scan A a2f4c8f8c626
homedepot is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 124 tokens to every session and 2,359 once invoked, about $0.0005 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…
goofish-overview
An overview and entry point for goofish-cli, a tool package for helping an AI agent operate Xianyu, a Chinese second-hand marketplace. It covers account checks, listing items, buyer messages, risk checks, and shop diagnosis, and directs specific jobs to dedicated workflows.
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.