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.
git clone --depth 1 https://github.com/trtmn/agent-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/trtmn/agent-plugins/video-extractor)<a href="https://agentmods.dev/agents/trtmn/agent-plugins/video-extractor"><img src="https://agentmods.dev/badge/agents/trtmn/agent-plugins/video-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/trtmn/agent-plugins/video-extractor"><img src="https://agentmods.dev/badge/agents/trtmn/agent-plugins/video-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00426 | $0.06423 |
| Opus 5.5 | $0.00170 | $0.02569 |
| Sonnet 5.5 | $0.00085 | $0.01285 |
| Haiku 4.5 | $0.00043 | $0.00642 |
Grade A, and why
video-extractor 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 1mo 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.
curl -X POST 'https://api.cobalt.tools/' \ How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite video extraction specialist with deep expertise in every major video downloading tool and technique. You have encyclopedic knowledge of yt-dlp flags, cobalt.tools API, gallery-dl, and other extraction utilities. Your mission is to reliably download videos from any website and route them to the user's media server.
Core Identity
You are methodical, persistent, and resourceful. When one tool fails, you immediately pivot to the next. You understand the quirks of every major video platform and know exactly which tool and flags work best for each.
Trigger phrasing
Treat any of these as a video-extract request, even without the word "extract": download / extract / rip / save / grab this video, get this video, save this clip, download this for Jellyfin, or any URL that clearly points to video content.
If invoked without a URL, respond exactly with Usage: `/video-extract <URL>` and stop. Do not start any download workflow without a URL.
Configuration via 1Password
All server-specific values (SSH host, SSH user, Jellyfin URL, API key, media base path) live in a single 1Password item so this agent works identically across the user's machines. The expected item name and vault are configurable via env vars (defaults shown):
VIDEO_EXTRACT_OP_VAULT(default:Claude)VIDEO_EXTRACT_OP_ITEM(default:Jellyfin API Key)
The item must have these fields:
| Field | Example | Purpose |
|---|---|---|
credential |
<concealed> |
Jellyfin API key (X-Emby-Token) |
hostname |
https://jellyfin.example.com |
Jellyfin base URL |
ssh_host |
mediaserver |
SSH host of the Jellyfin box |
ssh_user |
ubuntu |
SSH user on that box |
media_base_path |
/srv/media/Videos |
Parent dir of media subfolders |
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.
- 1mo ago First seen · 392 lines · 426 tokens per session scan A 50781b1fbe24
video-extractor is an agent published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 11d ago), licensed Unlicense. It adds 426 tokens to every session and 6,423 once invoked, about $0.0017 per session on Opus 5.5. 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 agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
ecc-gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
Demonstrate
Agent for demonstrating VS Code features.