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 zillowgit 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/zillow)<a href="https://agentmods.dev/skills/agentcomputerai/torch/zillow"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/zillow/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/zillow"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/zillow.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 | $0.00112 | $0.02381 |
| Opus 5.5 | $0.00045 | $0.00952 |
| Sonnet 5.5 | $0.00022 | $0.00476 |
| Haiku 4.5 | $0.00011 | $0.00238 |
Grade A, and why
zillow 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 zillow.com /homes/for_sale/ search pages. CloudFront + PerimeterX (HumanSecurity) gates raw curl with HTTP 403 `x-px-blocked: 1`. A puppeteer.connect() to the user's real Chrome How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zillow (zillow.com)
Server-rendered Next.js search pages behind CloudFront + PerimeterX. Once a session is flagged ("Access to this page has been denied"), every subsequent navigation in that browser context returns the deny page until cookies are cleared. The fix is mechanical: clear cookies, hit Google first, then go to the search URL. After that, all 41 results for a city search are sitting in
__NEXT_DATA__as a single JSON blob — no API replay, no scrolling tricks needed.
Detection
| Signal | Value |
|---|---|
| CDN | CloudFront (server: CloudFront, via: 1.1 …cloudfront.net) |
| Anti-bot | PerimeterX / HumanSecurity (x-px-blocked: 1 on block, _px* cookies on allow) |
| Framework | Next.js (__NEXT_DATA__ JSON blob) |
| Auth | None for search results |
| Robots | Disallows /search-results, but /homes/ listing pages are public |
Bare curl/fetch returns HTTP 403 with a 5.8KB CAPTCHA HTML. Even a real Chrome session gets stuck on "Access to this page has been denied" once a previous tab in that profile got flagged — the deny verdict is sticky in cookies.
Architecture
/homes/for_sale/<city>-<state>/is server-rendered. The full first page of ~41 listings is embedded in<script id="__NEXT_DATA__" type="application/json">atprops.pageProps.searchPageState.cat1.searchResults.listResults(or any nestedlistResultsarray — walk the tree).- The zillow.com homepage and search pages share the same PerimeterX cookie (
_pxhd,_px3). A clean session fetched via Google → search URL gets a clean PX challenge that auto-passes. - Pagination uses
?searchQueryState=<urlencoded JSON>with apagination.currentPagefield. Cursor-style; not needed for a scout run.
Strategy used
- Phase 0 (curl): 403,
x-px-blocked: 1. Skip. - Phase 1 (framework recon): Confirmed Next.js, but couldn't fetch HTML to parse. Skip.
- Phase 2 (browser via the real Chrome debug port): Works after cookie clear + Google warmup. This is the canonical path.
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 · 182 lines · 0 tokens per session scan A 4d24b64f7d62
zillow is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 112 tokens to every session and 2,381 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.