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 Demerzels-lab/elsamultiskillagent --skill youtube-summarizergit clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagentWrote 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/demerzels-lab/elsamultiskillagent/youtube-summarizer)<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/youtube-summarizer"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/youtube-summarizer/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/demerzels-lab/elsamultiskillagent/youtube-summarizer"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/youtube-summarizer.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 | $0.00040 | $0.01151 |
| Opus 5 | $0.00020 | $0.00575 |
| Sonnet 5 | $0.00008 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
youtube-summarizer 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 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.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Summarizer Skill
Automatically fetch transcripts from YouTube videos, generate structured summaries, and deliver full transcripts to messaging platforms.
When to Use
Activate this skill when:
- User shares a YouTube URL (youtube.com/watch, youtu.be, youtube.com/shorts)
- User asks to summarize or transcribe a YouTube video
- User requests information about a YouTube video's content
Dependencies
Required: MCP YouTube Transcript server must be installed at:
/root/clawd/mcp-server-youtube-transcript
If not present, install it:
cd /root/clawd
git clone https://github.com/kimtaeyoon83/mcp-server-youtube-transcript.git
cd mcp-server-youtube-transcript
npm install && npm run build
Workflow
1. Detect YouTube URL
Extract video ID from these patterns:
https://www.youtube.com/watch?v=VIDEO_IDhttps://youtu.be/VIDEO_IDhttps://www.youtube.com/shorts/VIDEO_ID- Direct video ID:
VIDEO_ID(11 characters)
2. Fetch Transcript
Run this command to get the transcript:
cd /root/clawd/mcp-server-youtube-transcript && node --input-type=module -e "
import { getSubtitles } from './dist/youtube-fetcher.js';
const result = await getSubtitles({ videoID: 'VIDEO_ID', lang: 'en' });
console.log(JSON.stringify(result, null, 2));
" > /tmp/yt-transcript.json
Replace VIDEO_ID with the extracted ID. Read the output from /tmp/yt-transcript.json.
3. Process the Data
Parse the JSON to extract:
result.metadata.title- Video titleresult.metadata.author- Channel nameresult.metadata.viewCount- Formatted view countresult.metadata.publishDate- Publication dateresult.actualLang- Language usedresult.lines- Array of transcript segments
Full text: result.lines.map(l => l.text).join(' ')
4. Generate Summary
Create a structured summary using this template:
📹 **Video:** [title]
👤 **Channel:** [author] | 👁️ **Views:** [views] | 📅 **Published:** [date]
**🎯 Main Thesis:**
[1-2 sentence core argument/message]
**💡 Key Insights:**
- [insight 1]
- [insight 2]
- [insight 3]
- [insight 4]
- [insight 5]
**📝 Notable Points:**
- [additional point 1]
- [additional point 2]
**🔑 Takeaway:**
[Practical application or conclusion]
What ships with it
4 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.
- 8d ago First seen · 162 lines · 40 tokens per session scan A 84e4b66cf730
youtube-summarizer is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,151 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
youtube-summarizer
Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.
youtube-transcribe
A tool that downloads YouTube videos or subtitles, turns speech into text, and can translate English into Chinese in a bilingual Markdown file.
youtube-watcher-zh
A YouTube subtitle tool that downloads available captions with yt-dlp and uses them to summarize videos, answer questions, search for terms, and examine topics or word use.
youtube-research
Research and analyze YouTube video content. Get summaries, detailed notes, and insights from video transcripts.
youtube-transcribe
Transcribe YouTube videos and playlists. Extract audio to text with visual context, generate summaries and detailed notes.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.