Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lattifai/omni-captions-skillsnpx agentmods add skills/lattifai/omni-captions-skills/omnicaptions-downloadWrote 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/lattifai/omni-captions-skills/omnicaptions-download)<a href="https://agentmods.dev/skills/lattifai/omni-captions-skills/omnicaptions-download"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-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/lattifai/omni-captions-skills/omnicaptions-download"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-download.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 | $0.00027 | $0.01172 |
| Opus 5 | $0.00014 | $0.00586 |
| Sonnet 5 | $0.00005 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
omnicaptions-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 12d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Download from Video Platforms
Download videos, audio, and captions from YouTube and 1000+ video platforms using yt-dlp.
Confirmation Required
IMPORTANT: Before executing any download, you MUST confirm with the user using AskUserQuestion:
- Show the URL to download
- Show the quality setting (audio/video)
- Show the output directory
- Ask for confirmation
Example confirmation:
Ready to download:
- URL: https://youtube.com/watch?v=xxx
- Type: Audio only / Video (1080p)
- Save to: Current directory
Confirm download?
Only proceed with the download command after user confirms.
When to Use
- Download YouTube videos/audio for offline use
- Extract captions from video platforms
- Get audio for local transcription or editing
When NOT to Use
- Just need transcription (use
/omnicaptions:transcribe- Gemini handles URLs directly) - Converting existing caption formats (use
/omnicaptions:convert)
Setup
pip install omni-captions-skills --extra-index-url https://lattifai.github.io/pypi/simple/
CLI Usage
Note: By default, files are saved to the current working directory. Do not specify -o unless the user explicitly requests a different location.
# Download audio only (default, saves to current directory)
omnicaptions download "https://www.youtube.com/watch?v=VIDEO_ID"
# Supports bare YouTube video ID (auto-validates via yt-dlp)
omnicaptions download e882eXLtwkI
# Download video (1080p recommended)
omnicaptions download "https://youtube.com/watch?v=VIDEO_ID" -q 1080p
# Only use -o when user explicitly requests a different location
omnicaptions download "https://youtube.com/watch?v=VIDEO_ID" -o ./downloads/
| Option | Description |
|---|---|
-o, --output |
Output directory (default: current) |
-q, --quality |
Quality: audio (default), best, 1080p, 720p, 480p, 360p |
-v, --verbose |
Verbose output |
Quality Presets
| Preset | Description |
|---|---|
audio |
Audio only (m4a/mp3), smallest size |
1080p |
1080p video + audio (recommended for video) |
720p |
720p video + audio |
480p |
480p video + audio |
360p |
360p video + audio |
best |
Best available quality (may be 4K+, very large) |
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.
- 12d ago First seen · 136 lines · 27 tokens per session scan A 0e0d345bcf91
omnicaptions-download is a skill published in the GitHub repository lattifai/omni-captions-skills (22 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,172 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…