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/pypinpx skills add AgentComputerAI/torch --skill pypigit 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 | $0.00079 | $0.01675 |
| Opus 5 | $0.00039 | $0.00838 |
| Sonnet 5 | $0.00016 | $0.00335 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
pypi 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 2d 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.
- **Phase 0 (curl)**: immediately saw FullStory Client Challenge on `/search/`. Skipped browser entirely. How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyPI (pypi.org)
PyPI (Warehouse) exposes official RSS feeds and a JSON API that return the same data the /search HTML page would, without any anti-bot. The HTML /search endpoint is protected by a FullStory client challenge — don't bother with a browser.
Detection
| Signal | Value |
|---|---|
| Server | gunicorn (Warehouse, the PyPI codebase) |
| CDN | Fastly (x-served-by: cache-*) |
| Anti-bot | FullStory client challenge on /search/* (/_fs-ch-*/script.js) — serves a Client Challenge HTML stub to non-JS clients |
| Auth | Not needed |
| robots.txt | Disallows /simple/ indexes; RSS feeds and JSON API are fine |
Curl https://pypi.org/search/?q=&o=-created returns <title>Client Challenge</title> with a /_fs-ch-1T1wmsGaOgGaSxcX/script.js loader. A plain Chrome UA does not bypass it. Don't waste time — use the feeds.
Architecture
PyPI is served by Warehouse. It exposes three scraper-friendly data sources that completely replace the need to scrape HTML:
- RSS feeds (XML, unauthenticated, no anti-bot):
https://pypi.org/rss/packages.xml— 40 newest packages (first release only). This is the equivalent of/search/?q=&o=-created.https://pypi.org/rss/updates.xml— 40 newest releases (includes new versions of existing packages).https://pypi.org/rss/project/<name>/releases.xml— per-project release feed.
- JSON API (unauthenticated):
https://pypi.org/pypi/<name>/json— full metadata for a package (description, author, classifiers, URLs, all releases, file hashes).https://pypi.org/pypi/<name>/<version>/json— metadata for a specific release.
- BigQuery / Google Cloud public dataset (
bigquery-public-data.pypi.*) — for bulk historical data, not scraping.
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.
- 2d ago First seen · 122 lines · 79 tokens per session scan A 9f809293db79
pypi is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,675 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.
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…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…