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 biggora/claude-plugins-registry --skill youtube-searchgit clone --depth 1 https://github.com/biggora/claude-plugins-registryWrote 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/biggora/claude-plugins-registry/youtube-search)<a href="https://agentmods.dev/skills/biggora/claude-plugins-registry/youtube-search"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/youtube-search/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/biggora/claude-plugins-registry/youtube-search"><img src="https://agentmods.dev/badge/skills/biggora/claude-plugins-registry/youtube-search.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 | $0.00129 | $0.03429 |
| Opus 5 | $0.00064 | $0.01715 |
| Sonnet 5 | $0.00026 | $0.00686 |
| Haiku 4.5 | $0.00013 | $0.00343 |
Grade A, and why
youtube-search scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.get(f"{BASE}/search", params=params) How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Search Skill
Autonomous YouTube data retrieval for agents. No user intervention required.
Method Selection Guide
Choose based on what's configured in the project environment:
| Situation | Best Method |
|---|---|
| Deep scraping needed (default) | Method E – yt-dlp (environment-dependent) |
| No API keys available | Method A – web_search built-in tool |
YOUTUBE_API_KEY set |
Method B – YouTube Data API v3 (richest data) |
SERPAPI_KEY set |
Method C – SerpAPI YouTube engine |
| Video ID known, need transcript | Method D – youtube-transcript-api |
Start with Method A if you're unsure — it requires nothing and always works.
Method A: web_search tool (Zero Setup — Always Available)
Use the built-in web_search tool. Works without any API keys.
Video Search
web_search("site:youtube.com <your query>")
Channel Search
web_search("site:youtube.com/channel <channel name> OR site:youtube.com/@<handle>")
Advanced Filters via Query
# Recent videos (last year)
web_search("site:youtube.com <query> 2024 OR 2025")
# Tutorial videos
web_search("site:youtube.com <topic> tutorial OR guide OR обзор")
# Specific language
web_search("site:youtube.com <query> на русском")
What you get from web_search
- Video title
- Channel name
- URL (extract video ID:
youtube.com/watch?v=VIDEO_ID) - Snippet/description excerpt
- Sometimes view count and publish date (in snippet)
Extract Video ID from URL
import re
url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
video_id = re.search(r'v=([^&]+)', url).group(1)
# or from youtu.be links:
video_id = re.search(r'youtu\.be/([^?]+)', url).group(1)
Limitation: No structured JSON, metadata is text-parsed. For richer data, use Method B.
Method B: YouTube Data API v3 (Recommended for Production)
Requires: YOUTUBE_API_KEY environment variable (free, 10,000 units/day quota).
Get key: https://console.cloud.google.com → Enable "YouTube Data API v3" → Create API key.
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.
- 9d ago First seen · 412 lines · 129 tokens per session scan A ea4d2e78d906
youtube-search is a skill published in the GitHub repository biggora/claude-plugins-registry (2 stars, last pushed 11d ago), licensed MIT. It adds 129 tokens to every session and 3,429 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…