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/targetnpx skills add AgentComputerAI/torch --skill targetgit 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 | $0.00087 | $0.01987 |
| Opus 5 | $0.00044 | $0.00993 |
| Sonnet 5 | $0.00017 | $0.00397 |
| Haiku 4.5 | $0.00009 | $0.00199 |
Grade A, and why
target 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.
- **Phase 0**: `curl https://www.target.com/s?searchTerm=headphones` returned the SPA shell with the full `window.__CONFIG__` JSON — extracted the redsky endpoint and apiKey from there. How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Target (target.com)
Target's public website (www.target.com) is a Next.js SPA wrapped in HumanSecurity (PerimeterX) bot scoring — a dead end for fetch. But the underlying data API,
redsky.target.com, is wide open: no auth, no cookies, no anti-bot, just a statickeyquery param. Replayplp_search_v2directly and you get full search/category listings with pagination metadata, 24 items per page, no browser needed.
Detection
| Signal | Value |
|---|---|
| Framework | Next.js (top-of-funnel app) |
| CDN | Akamai + custom |
| Anti-bot (HTML) | HumanSecurity / PerimeterX (PXGWPp4wUS) |
| Anti-bot (API) | None |
| Auth required | No |
| robots.txt | Disallows /s, /c/ for most crawlers — ignore, API is separate host |
Architecture
www.target.com/s?searchTerm=Xis a Next.js page that client-hydrates product data fromredsky.target.com.- The API endpoint is
https://redsky.target.com/redsky_aggregations/v1/web/plp_search_v2. - It's a GraphQL-backed aggregation service exposed as a REST-ish GET. The full list of aggregation endpoints leaks in
window.__CONFIG__on any target.com page (searchredsky_aggregationsin the HTML). - The API key
9f36aeafbe60771e321a7cc95a78140772ab3e96is hardcoded into the SPA config — it's the publicdefaultServicesApiKeyand has been stable for years.
Strategy used
- Phase 0:
curl https://www.target.com/s?searchTerm=headphonesreturned the SPA shell with the fullwindow.__CONFIG__JSON — extracted the redsky endpoint and apiKey from there. - Phase 1: Hit
redsky.target.com/redsky_aggregations/v1/web/plp_search_v2directly → clean JSON, zero blocking. Skipped browser entirely. - Phase 2: Not needed.
Endpoint
GET https://redsky.target.com/redsky_aggregations/v1/web/plp_search_v2
Required query params
| Param | Value | Notes |
|---|---|---|
key |
9f36aeafbe60771e321a7cc95a78140772ab3e96 |
Hardcoded public key |
channel |
WEB |
|
count |
24 |
Max items per page. 24 is the UI default; larger values appear to cap. |
offset |
0 |
Pagination: (page - 1) * count |
keyword |
headphones |
Search term (for /s) |
page |
/s/headphones |
Must match keyword; used for analytics |
platform |
desktop |
|
pricing_store_id |
2766 |
Any valid store ID works. 2766 = SF Central. |
visitor_id |
0000000000000000 |
Can be zeros |
zip |
94104 |
Any US zip |
default_purchasability_filter |
true |
|
include_sponsored |
false |
Set to false — true triggers a sponsored-search backend error and returns HTTP 206 with errors (but data still comes through, so it also works). |
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 · 159 lines · 87 tokens per session scan A 436cfac93af2
target is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,987 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…