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 5.5 | $0.00045 | $0.00648 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (26 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,621 once invoked, about $0.0005 per session on Opus 5.5. 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
puppeteer-automation
Expert guidance for browser automation using Puppeteer with best practices for web scraping, testing, screenshot capture, and JavaScript execution in headless Chrome.
chrome-extension-development
Expert guidelines for Chrome extension development with Manifest V3, covering security, performance, and best practices. Use when building browser extensions, creating popup UIs, implementing content scripts, working with Chrome APIs, managing extension permissions, or publishing to Chrome Web Store.
playwright
Playwright end-to-end testing best practices for web applications, covering test design, locator strategies, and assertion patterns.
playwright-cursor-rules
Expert guidance for Playwright end-to-end testing with TypeScript and JavaScript best practices.
timescaledb-hyperfunctions
Use this skill when writing analytical SQL over time-series data with the TimescaleDB Toolkit (timescaledbtoolkit extension) hyperfunctions: approximate percentiles, statistical summaries, time-weighted averages, counter/gauge rates, uptime/heartbeat tracking, state durations, OHLC candlesticks, approximate distinct…
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.