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/nikenpx skills add AgentComputerAI/torch --skill nikegit 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 | $0.00086 | $0.02305 |
| Opus 5 | $0.00043 | $0.01153 |
| Sonnet 5 | $0.00017 | $0.00461 |
| Haiku 4.5 | $0.00009 | $0.00231 |
Grade A, and why
nike 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.
const res = await fetch(url, { headers }); How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nike (nike.com)
Custom React SPA with SSR bootstrap ("Web Shell"). The product grid hydrates from an internal
api.nike.com/discover/product_wall/v1JSON API. There is no__NEXT_DATA__blob; only the first ~24 cards are server-rendered, the rest load via XHR on scroll.Skip the browser entirely. Replay the API with
fetch. It's public, fast, and anti-bot-free — just send the right headers.
Detection
| Signal | Value |
|---|---|
| Framework | Custom React SPA with "Web Shell" SSR |
| API | api.nike.com/discover/product_wall/v1 — public JSON, cursor-paginated |
| Anti-bot | None on the API (for browsing). Akamai Bot Manager on www.nike.com, but the API bypasses it |
| Auth | Not required for catalog browse. SNKRS and checkout are gated. |
| Rate limit | None observed at ~7 req/s across 132 pages. 150ms sleep between pages is plenty. |
Strategy
Skip browser entirely
→ GET api.nike.com/discover/product_wall/v1/... with nike-api-caller-id header
→ Follow pages.next cursor until empty
→ Flatten productGroupings[].products[] to one row per colorway
Never launch Puppeteer for Nike catalog scraping — the API is faster, cleaner, and has no rate limits.
Endpoint template
US English "new releases" gridwall (/w/new-3n82y):
GET https://api.nike.com/discover/product_wall/v1/marketplace/US/language/en/consumerChannelId/d9a5bc42-4b9c-4976-858a-f159cf99c647
?path=/w/new-3n82y
&attributeIds=53e430ba-a5de-4881-8015-68eb1cff459f
&queryType=PRODUCTS
&anchor=0
&count=24
Parameters:
| Param | Value | Notes |
|---|---|---|
path |
The URL slug (e.g. /w/new-3n82y) |
Identifies the gridwall |
attributeIds |
GUID for the category filter | Sniff once per category (see Gotchas) |
queryType |
PRODUCTS |
Always |
anchor |
0, 24, 48, ... |
Pagination offset, increments by count |
count |
24 |
Required — larger values return HTTP 400 |
For other gridwalls, swap path and attributeIds to the target category's values. Find them by sniffing the page once in devtools.
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 · 220 lines · 86 tokens per session scan A c83e107982f9
nike is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 2,305 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.
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…