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/imdbnpx skills add AgentComputerAI/torch --skill imdbgit 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 | $0.00077 | $0.01712 |
| Opus 5 | $0.00039 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
Grade A, and why
imdb 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 imdb.com. Next.js SPA behind CloudFront + AWS WAF (x-amzn-waf-action challenge on raw curl). Real Chrome via the real Chrome debug port sails past the challenge on first navigati How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMDb (imdb.com)
Full catalog (charts, titles, names) is a Next.js app served via CloudFront with an AWS WAF challenge on bare curl requests. A real Chrome session (the real Chrome debug port) passes the challenge silently; __NEXT_DATA__ then yields a complete, typed JSON payload that's vastly richer than the DOM.
Detection
| Signal | Value |
|---|---|
| CDN | CloudFront (via: 1.1 ...cloudfront.net) |
| Framework | Next.js (__NEXT_DATA__ present, /_next/ assets) |
| Anti-bot | AWS WAF — returns HTTP/2 202 + x-amzn-waf-action: challenge + empty body to plain curl, even with spoofed UA/headers |
| Auth | Not required for public chart/title/name pages |
| robots.txt | Allows most public paths; disallows /search/, /find, etc. |
Architecture
- Next.js SSR: every chart/title page inlines a
<script id="__NEXT_DATA__">JSON blob with the full page payload already resolved. - Chart pages (
/chart/top,/chart/moviemeter,/chart/boxoffice, …) expose the list atprops.pageProps.pageData.chartTitles.edges[].node. - Each node has
id(tconst),titleText,releaseYear,runtime,ratingsSummary(aggregateRating + voteCount),certificate,titleGenres,primaryImage, etc. — no DOM scraping needed.
Strategy used
- Phase 0 (curl): blocked.
HTTP/2 202+x-amzn-waf-action: challenge, zero body. Don't waste time tweaking headers — AWS WAF is JS-challenge based. - Phase 1 (framework): skipped as a standalone fetch path — same WAF wall — but
__NEXT_DATA__is the extraction target once the page loads in a browser. - Phase 2 (browser):
puppeteer.connect({ browserURL: the real Chrome debug port }). Real Chrome clears WAF on the first navigation with no interaction. No stealth plugin, no captcha solver, no proxy.
Stealth config that works
import puppeteer from "puppeteer-core";
const browser = await puppeteer.connect({ browserURL: "http://127.0.0.1:9222" });
const page = await browser.newPage();
await page.goto("https://www.imdb.com/chart/top/", { waitUntil: "domcontentloaded", timeout: 45000 });
await page.waitForSelector("li.ipc-metadata-list-summary-item");
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 · 129 lines · 77 tokens per session scan A 531f11d25924
imdb is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 1,712 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
br3eze-code
AgentOS uses a modular 3-tier ReAct reasoning engine. The AI (Gemini 2.0 Flash / Claude Sonnet 4.6 / GPT-4o / Ollama) automatically discovers, chains, and executes these skills via the Tool Registry and Skill Loader.
agentos-security-remediation
Review and remediate Dependabot and dependency vulnerabilities in AgentOS repositories. Use for critical or high-severity alert triage, dependency-path analysis, specialist assignment, secure upgrades, regression testing, rollback planning, release gates, and audit evidence.
agentos-specialist-swarm
Coordinate AgentOS specialist work across Planner, Engineer, Accountant, Secretary, Procurement, Expeditor, Designer, and Draftsman roles. Use for role onboarding, WBS delegation, skill selection, activity tracking, handoffs, approvals, evidence, channel rendering, procurement exceptions, and project delivery…
agentos-expeditor
Coordinate AgentOS fulfillment and delivery work with milestones, supplier and courier tracking, exception handling, recovery options, Procurement handoffs, escalation approvals, evidence, and receipt closure. Use for order delays, shipment tracking, vendor exceptions, and delivery recovery.
agentos-role-skill-factory
Create, validate, integrate, and release separate AgentOS role-skill packages with SKILL.md instructions and index.js entry points. Use when adding a specialist role, generating role metadata, wiring WBS and approval contracts, or packaging role skills for the repository.
agentos-designer
Design user, service, and system solutions in AgentOS from scoped requirements, constraints, alternatives, prototypes, reviews, acceptance criteria, and controlled publication. Use for design briefs, concepts, UX, service flows, architecture proposals, and design changes.