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 Mathews-Tom/armory --skill youtube-searchgit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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/mathews-tom/armory/youtube-search)<a href="https://agentmods.dev/skills/mathews-tom/armory/youtube-search"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/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/mathews-tom/armory/youtube-search"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/youtube-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.02006 |
| Opus 5.5 | $0.00029 | $0.00802 |
| Sonnet 5.5 | $0.00015 | $0.00401 |
| Haiku 4.5 | $0.00007 | $0.00201 |
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 10d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Search
Search YouTube by keyword and return structured video metadata — title, URL,
channel, views, duration, upload date. Uses yt-dlp for scraping with no API
keys or OAuth required.
Prerequisites
uv tool install yt-dlp
Verify:
yt-dlp --version
Usage
Basic Search
yt-dlp "ytsearch10:claude code skills" --dump-json --flat-playlist --no-warnings 2>/dev/null \
| jq -r '[.title, .url, .channel, .view_count, .duration_string, .upload_date] | @tsv'
ytsearch10:— search YouTube, return 10 results (adjust number as needed)--dump-json— output metadata as JSON--flat-playlist— don't download, just list--no-warnings— suppress non-error output
Structured JSON Output
yt-dlp "ytsearch5:claude code mcp servers" \
--dump-json --flat-playlist --no-warnings 2>/dev/null \
| jq '{
title: .title,
url: .url,
channel: .channel,
views: .view_count,
duration: .duration_string,
upload_date: .upload_date,
description: (.description // "" | .[0:200])
}'
Search with Sorting
yt-dlp does not support server-side sort. To sort by views or date, capture all results and sort client-side:
# Sort by view count (descending)
yt-dlp "ytsearch20:AI agents 2026" \
--dump-json --flat-playlist --no-warnings 2>/dev/null \
| jq -s 'sort_by(-.view_count) | .[:10][] | {title, url, channel, views: .view_count}'
# Sort by upload date (newest first)
yt-dlp "ytsearch20:claude code tutorial" \
--dump-json --flat-playlist --no-warnings 2>/dev/null \
| jq -s 'sort_by(-.upload_date) | .[:10][] | {title, url, channel, upload_date}'
Search Result Count
The number after ytsearch controls how many results to fetch:
| Pattern | Results |
|---|---|
ytsearch5:query |
5 results |
ytsearch10:query |
10 results (default recommendation) |
ytsearch20:query |
20 results |
ytsearch50:query |
50 results (slow, may hit rate limits) |
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.
- 10d ago Changed 53f11e1ad534
- 1mo ago First seen · 233 lines · 73 tokens per session scan A d5f59a9ced0c
youtube-search is a skill published in the GitHub repository Mathews-Tom/armory (332 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 2,006 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
browser
Drive a live browser with async Python against QwenPaw's builtin Browser SDK. The full reference is below; re-load this browser skill after context compaction.
webmcp
Open a user-provided URL in the host's built-in browser and use the page's MCP or WebMCP tools before browser UI automation for app communication or edits.
an
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.