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/walmartnpx skills add AgentComputerAI/torch --skill walmartgit 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 | $0.00091 | $0.02268 |
| Opus 5 | $0.00046 | $0.01134 |
| Sonnet 5 | $0.00018 | $0.00454 |
| Haiku 4.5 | $0.00009 | $0.00227 |
Grade A, and why
walmart 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 yesterday.
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 walmart.com. Next.js SPA behind Akamai Bot Manager — curl is 307-redirected to /blocked, but a puppeteer connection to the user's real Chrome (`127.0.0.1:9222`) walks straight th How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walmart (walmart.com)
Walmart is a Next.js storefront fronted by Akamai Bot Manager. Anonymous curl/fetch is hard-blocked (307 →
/blocked?url=...&uuid=...), and a fresh Chromium — even with stealth — gets served interstitials and challenge pages. The single thing that makes it trivial is127.0.0.1:9222: connect to the user's real Chrome and Walmart treats you like a normal shopper. All listing data hydrates from an embedded__NEXT_DATA__JSON blob, so you don't need to reverse any internal APIs.
Detection
| Signal | Value |
|---|---|
| Framework | Next.js (<script id="__NEXT_DATA__"> on every page) |
| CDN / edge | Akamai (x-ak-protocol, ak_p server-timing, TS* cookies) |
| Anti-bot | Akamai Bot Manager + PerimeterX (_pxhd cookie, px-captcha challenges) |
| Auth | Not required for search/browse/PDP |
| robots.txt | Disallows /search for most bots — ignore at your own risk, rate-limit yourself |
Block signature from curl:
HTTP/2 307
location: /blocked?url=<base64>&uuid=<px-uuid>&vid=&g=b
set-cookie: _pxhd=...
Seeing any of /blocked?, _pxhd, or the string "Robot or human" in the body means you're shadow-blocked.
Architecture
- Next.js SSR — the initial HTML already contains the full product grid as JSON inside
<script id="__NEXT_DATA__">. - The grid lives at
props.pageProps.initialData.searchResult.itemStacks[*].items[*], but there are severalitemStacks(main grid, sponsored rails, "popular in category"). Walk the tree and dedupe byusItemId. - Pagination is pure querystring:
&page=1..N. Each page returns ~48–50 items. No cursor, no infinite scroll fallback needed for search results. - PDPs follow the same pattern — hydrated product state in
__NEXT_DATA__.
Strategy used
- Phase 0 (curl): 307 →
/blocked. Skipped. - Phase 1 (framework): Next.js confirmed, but you can't get the HTML without a browser. Skipped.
- Phase 2 (browser):
puppeteer-core.connect({ browserURL: the real Chrome debug port }). No stealth, no cookies, no headers set — the real Chrome profile is already trusted. Walks in on the first try, parses__NEXT_DATA__, done.
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.
- yesterday First seen · 170 lines · 91 tokens per session scan A ef3966845e66
walmart is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 2,268 once invoked, about $0.0005 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.
browserstack
../../../engineering-team/playwright-pro/skills/browserstack/SKILL.md.
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
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…
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…