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 MSApps-Mobile/claude-plugins --skill youtube-transcribergit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/youtube-transcriber)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/youtube-transcriber"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/youtube-transcriber/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/msapps-mobile/claude-plugins/youtube-transcriber"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/youtube-transcriber.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 | $0.00116 | $0.01954 |
| Opus 5.5 | $0.00046 | $0.00782 |
| Sonnet 5.5 | $0.00023 | $0.00391 |
| Haiku 4.5 | $0.00012 | $0.00195 |
Grade A, and why
youtube-transcriber 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 1mo 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Transcriber
Extract transcripts from YouTube videos and playlists using browser-based caption extraction. Works with any video that has auto-generated or manual captions — no API key required.
Environment note: This skill works in both Claude Code and Cowork. It requires the Claude in Chrome extension in both environments. The Chrome MCP tools (
navigate,javascript_tool,get_page_text, etc.) work identically in both.
Prerequisites
This skill requires Claude in Chrome (browser automation). If the Chrome MCP tools
(navigate, javascript_tool, get_page_text, etc.) are not available, inform the user:
- Cowork: "Install the Claude in Chrome extension from your browser"
- Claude Code: "Add the Chrome MCP extension and ensure it's running"
Single Video Transcription
Step 1: Navigate to the video
navigate to: https://www.youtube.com/watch?v={VIDEO_ID}
Wait for the page to load. If given a short URL (youtu.be/ID) or a URL with extra params, extract the video ID and use the canonical format above.
Step 2: Expand the description to reveal the transcript button
Use javascript_tool to click "...more" on the description:
const expandBtn = document.querySelector('#description-inline-expander #expand')
|| document.querySelector('tp-yt-paper-button#expand');
if (expandBtn) expandBtn.click();
Wait 1-2 seconds for the description to expand.
Step 3: Open the transcript panel
Use javascript_tool to find and click the "Show transcript" button:
const buttons = document.querySelectorAll('button.yt-spec-button-shape-next');
let clicked = false;
buttons.forEach(b => {
if (b.innerText.includes('Show transcript') || b.innerText.includes('הצגת תמליל') || b.innerText.includes('להצגת התמליל')) {
b.click();
clicked = true;
}
});
clicked ? 'Transcript panel opened' : 'Show transcript button not found';
Wait 2 seconds for the transcript panel to load.
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.
- 1mo ago First seen · 254 lines · 116 tokens per session scan A 01e0b95e909c
youtube-transcriber is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 1,954 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 2026-09-13.
Other skills, from other repositories
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
url2ebook
A web-page converter that fetches the main content from a URL and creates an ebook for offline reading. The output is generated as an ebook file.
html-to-markdown-extracting-metadata
Use when extracting metadata from HTML — title, description, language, Open Graph, JSON-LD / Microdata / RDFa, headers, links, and images. Covers the --json output shape and the --extract-metadata flag.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
doc-html-report
A report renderer that turns Markdown into a single HTML file you can open in a browser. The file works for email attachments, printing, and offline viewing.
doc-docx
A Word document generator for editable DOCX files, the standard format used by Microsoft Word. It creates reports, contracts, proposals, official letters, and planning documents using Korean office layouts and a defined visual style.