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 skills add cosmicstack-labs/mercury-agent-skills --skill video-downloadergit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/skills/cosmicstack-labs/mercury-agent-skills/video-downloader)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/video-downloader"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/video-downloader/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/skills/cosmicstack-labs/mercury-agent-skills/video-downloader"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/video-downloader.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 | $0.00029 | $0.04384 |
| Opus 5 | $0.00015 | $0.02192 |
| Sonnet 5 | $0.00006 | $0.00877 |
| Haiku 4.5 | $0.00003 | $0.00438 |
Grade D, and why
video-downloader scanned grade D with 2 findings 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install yt-dlp ffmpeg Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
# Use netrc file (~/.netrc) How it starts
The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Downloader
Download videos from thousands of sites using yt-dlp — the most powerful and actively maintained video downloading tool. This skill covers installation, configuration, format selection, playlist management, and optimization techniques.
Core Principles
1. Choose the Right Tool
yt-dlp is the successor to youtube-dl and is actively maintained with support for over 1,000 sites. It handles YouTube, Bilibili, Twitter/X, Instagram, TikTok, Vimeo, Twitch, and countless others through extractors.
2. Understand Format Selection
Video and audio are often delivered as separate streams (DASH). yt-dlp can merge them automatically with ffmpeg, or you can download them individually. Understanding formats means you get exactly the quality you need without wasting bandwidth.
3. Respect Rate Limits and Servers
Don't hammer servers with concurrent downloads. Use rate limiting, randomized delays, and reasonable thread counts to avoid IP blocks and maintain access.
4. Handle Authentication Properly
Some content requires authentication. Use cookies from your browser session rather than passing passwords directly. This is more reliable and avoids credential exposure in command history.
Installation and Setup
macOS (Homebrew)
# Install yt-dlp
brew install yt-dlp
# Install ffmpeg for post-processing (merging, conversion)
brew install ffmpeg
Linux (Ubuntu/Debian)
# Latest version via pip (recommended)
python3 -m pip install -U yt-dlp
# Or via apt (may be outdated)
sudo apt install yt-dlp ffmpeg
Windows
# Via pip (recommended)
python -m pip install -U yt-dlp
# Via winget
winget install yt-dlp
# Download standalone binary
# https://github.com/yt-dlp/yt-dlp/releases
Verify Installation
yt-dlp --version
yt-dlp --help | head -20
Basic Download Commands
Simple Video Download
# Download best quality video+audio
yt-dlp "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
# Download with specific output template
yt-dlp -o "%(title)s.%(ext)s" "https://youtube.com/watch?v=VIDEO_ID"
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.
- 8d ago First seen · 563 lines · 29 tokens per session scan D 11abfa0d5573
video-downloader is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 17d ago), licensed MIT. It adds 29 tokens to every session and 4,384 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
muapi-media-generation
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.
wechat-article-writer
A Chinese-language content-creation workflow for public-account and social-media writing. It supports article drafting, cover images, illustrations, process diagrams, style analysis, and adapting writing to selected styles.
gemini-watermark-remover
Remove visible Gemini image watermarks from local image files by calling the project's CLI. Use when the user wants an agent to clean one or more local Gemini-generated images and save de-watermarked output files.