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 maystudios/claude-skills --skill video-downloadgit clone --depth 1 https://github.com/maystudios/claude-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/maystudios/claude-skills/video-download)<a href="https://agentmods.dev/skills/maystudios/claude-skills/video-download"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/video-download/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/maystudios/claude-skills/video-download"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/video-download.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 46 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Privilege Escalation · line 106 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00113 | $0.01621 |
| Opus 5 | $0.00056 | $0.00811 |
| Sonnet 5 | $0.00023 | $0.00324 |
| Haiku 4.5 | $0.00011 | $0.00162 |
Grade A, and why
video-download scanned grade A with 0 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Download Skill
Wraps yt-dlp with automatic recovery for YouTube anti-bot challenges.
Tool
scripts/download.py — installs yt-dlp on first run, merges video+audio to MP4,
auto-rotates strategies on bot detection, uses a download-archive for safe resume.
Workflow
- Collect all URLs from the user's request.
- Determine output directory (current working directory if unspecified).
- Decide single-video vs playlist mode:
- User says "this video" / single URL → leave default (single-video).
- User says "playlist" / "all videos" / passes a
playlist?list=URL → add--playlist.
- Run the script. If YouTube bot detection hits, the script auto-rotates strategies.
- Report which files were saved and which strategy worked.
Usage
# Single video, current directory
python scripts/download.py "https://www.youtube.com/watch?v=..."
# Multiple URLs to a folder
python scripts/download.py "URL1" "URL2" -o "/path/to/output"
# Full playlist as 720p MP4
python scripts/download.py "https://www.youtube.com/playlist?list=..." --playlist -o "./out"
# Force a specific browser for cookies (skips auto-rotation)
python scripts/download.py "URL" --cookies-from-browser chrome
# Force a manual cookies.txt file
python scripts/download.py "URL" --cookies "~/Downloads/www.youtube.com_cookies.txt"
# Higher quality
python scripts/download.py "URL" --max-height 1080
Flags
| Flag | Default | Notes |
|---|---|---|
-o, --output |
cwd | Output directory |
--max-height |
720 | Max video height (e.g. 1080, 480) |
--playlist |
off | Download full playlist; default is single-video |
--cookies-from-browser |
auto | Force one browser; skips auto-rotation |
--cookies |
auto | Force one cookies.txt file; skips auto-rotation |
--no-archive |
off | Disable .download-archive.txt resume tracking |
Auto-Recovery Strategy Chain
When a request fails with bot-detection markers (Sign in to confirm,
LOGIN_REQUIRED), the script automatically advances through these strategies
in order, stopping at the first one that succeeds:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 161 lines · 113 tokens per session scan A d21821037817
video-download is a skill published in the GitHub repository maystudios/claude-skills (22 stars, last pushed 26d ago), licensed MIT. It adds 113 tokens to every session and 1,621 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
video-download
Collects videos from public social accounts. Use to download or scrape from Twitter, TikTok, YouTube, Instagram, or Facebook.
video-downloader
A downloader for videos from platforms including Douyin, Xiaohongshu, Kuaishou, WeChat Channels, Bilibili, YouTube, and Instagram. It provides videos without visible watermarks where available.
instagram-video-downloader
A tool that reads an Instagram video link and returns a link for downloading the video without a watermark. Instagram is a social platform for photos and videos.
twitter-video-downloader
A tool for turning an X (formerly Twitter) video link into a direct download link for the video without its visible watermark.
website-to-video
Website-to-video capture pack for turning product pages, flows, and browser states into structured video scenes.
presentation-chef
Convert any content into a stunning Apple Keynote-style HTML presentation. Takes markdown, text descriptions, or structured data and generates a single self-contained .html file with cinematic animations, glassmorphism, and premium design. Inspired by ChronicleHQ.