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 humancto/indic-voice-pipeline --skill video-downloadergit clone --depth 1 https://github.com/humancto/indic-voice-pipelineWrote 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/humancto/indic-voice-pipeline/video-downloader)<a href="https://agentmods.dev/skills/humancto/indic-voice-pipeline/video-downloader"><img src="https://agentmods.dev/badge/skills/humancto/indic-voice-pipeline/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/humancto/indic-voice-pipeline/video-downloader"><img src="https://agentmods.dev/badge/skills/humancto/indic-voice-pipeline/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 | $0.00097 | $0.01170 |
| Opus 5 | $0.00048 | $0.00585 |
| Sonnet 5 | $0.00019 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
video-downloader 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Downloader
Download videos, audio, and playlists from any URL. Supports 1000+ sites via yt-dlp.
Prerequisites
Run once to install dependencies:
pip install yt-dlp --quiet
ffmpeg is also required for audio extraction and format merging:
brew install ffmpeg # macOS
Step-by-Step Workflow
For ANY video download request, follow these steps:
Step 1: Check dependencies
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/check_deps.py
Step 2: Determine intent and run the appropriate command
User wants to download a video:
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>" --output-dir ~/Downloads
User wants audio only (music, podcast, etc.):
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py audio "<URL>" --output-dir ~/Downloads --audio-format mp3
User wants a full playlist:
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py playlist "<URL>" --output-dir ~/Downloads
User wants to see available formats/qualities:
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py formats "<URL>"
User wants video info without downloading:
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py info "<URL>"
Step 3: Report results
Tell the user:
- Where the file was saved (full path)
- File size
- Video title and duration
- Any subtitles that were downloaded
All Commands
# Download single video (default: best quality up to 1080p, saved to ~/Downloads)
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>"
# Download with quality cap
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>" --quality 720
# Download with specific format ID (use 'formats' command to find IDs)
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>" --format 137
# Download without subtitles
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>" --no-subs
# Download to custom directory
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py download "<URL>" --output-dir ~/Videos
# Download audio only as MP3
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py audio "<URL>"
# Download audio as M4A or Opus
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py audio "<URL>" --audio-format m4a
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py audio "<URL>" --audio-format opus
# Download entire playlist
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py playlist "<URL>"
# List available formats
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py formats "<URL>"
# Show video info without downloading
/usr/local/opt/[email protected]/bin/python3.11 ~/.claude/skills/video-downloader/scripts/video_downloader.py info "<URL>"
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 · 126 lines · 97 tokens per session scan A 4593fc749f67
video-downloader is a skill published in the GitHub repository humancto/indic-voice-pipeline (1 stars, last pushed 6mo ago), licensed MIT. It adds 97 tokens to every session and 1,170 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
video-recap
An end-to-end workflow for turning a video into a Chinese narrated recap. It coordinates video analysis, story planning, editing, voice generation, and final audio and subtitle assembly.
video-script
A Chinese-language video editing and narration workflow that plans the story, selects clips, assigns visuals and sound, writes timestamped narration, and validates the result.
video-assemble
A video finishing tool that combines a source video with recorded narration, adjusted original sound, and subtitles. It can create subtitle files, burn them into the video, and optionally standardise loudness.
video-cut
A video-editing skill that turns selected time ranges from a long source video into a shorter video. It follows decisions recorded in a clip plan and can also map an existing narration timeline to the edited result.
video-voiceover
A text-to-speech tool that turns a timestamped narration script into separate Chinese voice clips and places them within the video's timeline. Text-to-speech means generating spoken audio from written words.
video-understanding
A video analysis tool that turns a video into a structured index of scenes, spoken words, visual observations, quiet sections, and a writing brief. ASR means automatic speech recognition, which converts speech in the video into timestamped text.