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 valtterimelkko/agent-workflow-skills --skill youtube-searchgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote 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/valtterimelkko/agent-workflow-skills/youtube-search)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/youtube-search"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/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/valtterimelkko/agent-workflow-skills/youtube-search"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/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 | $0.00040 | $0.01439 |
| Opus 5 | $0.00020 | $0.00720 |
| Sonnet 5 | $0.00008 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
youtube-search 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search YouTube Videos
Search for YouTube videos using the YouTube Data API v3. Find videos by query across all of YouTube or within specific channels.
Prerequisites
YouTube API Key available in the environment or a shell startup file such as ~/.bashrc:
export YOUTUBE_API_KEY="your-api-key-here"
Get one from Google Cloud Console: Create project → Enable YouTube Data API v3 → Create API Key.
Daily quota: 10,000 units (each search ≈ 100 units, channel resolution ≈ 1 unit, playlist fetch ≈ 1 unit).
When to Use
- Search videos by topic or channel
- Filter by date, duration, sort order
- Get up to 50 results per query
Quick Start
Basic search:
python3 ./scripts/youtube_search.py --query "AI tutorials" --max-results 10
Channel-specific (if you already have the channel ID):
python3 ./scripts/youtube_search.py --query "Python" --channel-id "UC123..." --max-results 20
Parameters
| Parameter | Required | Default | Notes |
|---|---|---|---|
--query or -q |
Yes | - | Search term |
--channel-id or -c |
No | - | If provided, search only in this channel |
--max-results or -m |
No | 10 | Max 50 (preserves quota and LLM context) |
--order or -o |
No | relevance | date, rating, relevance, viewCount |
--published-after |
No | - | ISO 8601 format (e.g., "2025-01-01T00:00:00Z") |
--published-before |
No | - | ISO 8601 format |
--video-duration or -d |
No | any | any, short (<4min), medium (4-20min), long (>20min) |
Helper Scripts (API Quota Warning)
⚠️ Each helper script uses API quota. Plan carefully before running multiple times.
1. youtube_channel_id.py - Resolve @handle to Channel ID
Cost: 1 unit per resolution
python3 ./scripts/youtube_channel_id.py --handle "@MetalSole"
2. youtube_channel_videos.py - List Channel Videos
Cost: 1-2 units for channel lookup + 1 unit per ~50 videos fetched
# By handle
python3 ./scripts/youtube_channel_videos.py --handle "@MetalSole" --max-results 50
# By channel ID (saves quota - skips handle resolution)
python3 ./scripts/youtube_channel_videos.py --channel-id "UC123..." --max-results 50
# By playlist ID (cheapest - fastest method)
python3 ./scripts/youtube_channel_videos.py --playlist-id "UU123..." --max-results 50
What ships with it
5 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 · 153 lines · 40 tokens per session scan A 5c4fc127f784
youtube-search is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,439 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 2026-08-31.
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…