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/ikeanpx skills add AgentComputerAI/torch --skill ikeagit 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 | $0.00175 | $0.02274 |
| Opus 5 | $0.00088 | $0.01137 |
| Sonnet 5 | $0.00035 | $0.00455 |
| Haiku 4.5 | $0.00017 | $0.00227 |
Grade A, and why
ikea 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 ikea.com /cat/ category pages (PLP). Server-rendered HTML with 24 products per page embedded as `[data-testid="plp-product-card"]` blocks, each carrying `data-ref-id`, `data-prod How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IKEA (ikea.com)
IKEA PLPs are boring-good SSR HTML. Every product card is a fat
<div data-testid="plp-product-card">with all the important fields inline on data-attributes. The only real trap is Cloudflare's edge cache: plain curl gets a 200 but serves identical page-1 HTML for every?page=Nquery, so pagination has to go through a real browser (or cache-busting headers Cloudflare currently ignores). Real Chrome via127.0.0.1:9222walks through cleanly with zero challenges — no stealth, no proxy, no captcha.
Detection
| Signal | Value |
|---|---|
| CDN | Cloudflare (cf-ray, cf-cache-status: HIT, server: cloudflare) |
| Framework | Custom SSR (Java/Node "oink" backend — see cache-tag: prod-oink-*) |
| Anti-bot | None on HTML. Cloudflare only challenges API calls / write paths. |
| Auth | Not required for PLP, PDP, or category browse. |
| Cache quirk | ?page=N is cached but the cache KEY ignores the page param for anonymous curl — Chrome navigations resolve correctly. |
| robots.txt | Allows /us/en/cat/ (confirmed via sitemap links on the page). |
| Redirects | Some category slugs 301 to canonical (e.g. office-chairs-20652 → desk-chairs-20652). Follow Location. |
Architecture
-
Pure server-rendered HTML. No
__NEXT_DATA__, no GraphQL replay needed. -
24 products per
?page=N(even iftotalCountis smaller — last page shortcircuits). -
Total count is printed inline as
Showing 24 of 63 resultsinside.catalog-product-list__total-count. Parse it once on page 1 to know how many pages to crawl. -
Each card has all scrape-worthy fields on data-attributes — no need to traverse children for id/name/price:
<div class="plp-mastercard plp-fragment-wrapper plp-fragment-wrapper--grid" data-ref-id="10601124" data-product-number="10601124" data-price="199.99" data-currency="USD" data-product-name="CENTERHALV" data-testid="plp-product-card"> … </div>
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 · 148 lines · 0 tokens per session scan A a4e85dc13dd8
ikea is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 175 tokens to every session and 2,274 once invoked, about $0.0009 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…