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 0xmariowu/Autosearch --skill youtubegit clone --depth 1 https://github.com/0xmariowu/AutosearchWrote 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/0xmariowu/autosearch/youtube)<a href="https://agentmods.dev/skills/0xmariowu/autosearch/youtube"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/youtube/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/0xmariowu/autosearch/youtube"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/youtube.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 | $0.00000 | $0.00611 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
youtube 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Attribution
Source: self-written, plan
autosearch-0418-channels-and-skills.md§ F002c.
name: youtube description: Use for video tutorial discovery, conference talks, technical walkthroughs, and product demos. version: 1 languages: [en, zh, mixed] methods:
- id: data_api_search impl: methods/data_api_v3.py requires: [env:YOUTUBE_API_KEY] rate_limit: {per_min: 100, per_hour: 10000} fallback_chain: [data_api_search] when_to_use: query_languages: [en, zh, mixed] query_types: [tutorial, conference-talk, walkthrough, demo] avoid_for: [latest-text-news] quality_hint: typical_yield: medium chinese_native: false layer: leaf domains: [video-audio] scenarios: [video-discovery, tutorial-video, conference-talk] model_tier: Fast experience_digest: experience.md
Overview
YouTube is the broadest video discovery channel in the stack for tutorials, talks, walkthroughs, and product demos. It is useful when the user wants audiovisual explanation, presenter context, or conference footage rather than text-first sources.
For autosearch coverage, this channel adds strong visual learning and long-form talk retrieval across both English and Chinese queries. It matters because many technical explanations are easier to validate from recorded demos and conference sessions than from short text summaries.
When to Choose It
- Choose it for tutorial and walkthrough queries where visual explanation is part of the answer.
- Choose it for conference talks, keynote sessions, and recorded technical presentations.
- Choose it for product demo discovery across English, Chinese, or mixed-language queries.
- Prefer it when channel reputation and video format matter more than text recency.
- Avoid it for latest text-only news where a news or social channel is a better primary source.
How To Search (Planned)
data_api_search- Call the YouTube Data API v3 search endpoint with query text, language hints, and video result filters.data_api_search- Follow up with video metadata fields such as title, channel, duration, publish time, description, and watch URL for normalization.data_api_search- Rank toward tutorials, talks, and demos instead of general entertainment matches by combining keyword and channel-level cues.
What ships with it
1 file 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.
- 12d ago First seen · 61 lines · 0 tokens per session scan A c6e1d3735d08
youtube is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 611 tokens. 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
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
portable-text-serialization
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…
development-assistant
Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.