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.
/plugin marketplace add intellectronica/agent-skillsnpx agentmods add plugins/intellectronica/agent-skills/youtube-transcriptgit clone --depth 1 https://github.com/intellectronica/agent-skillsGrade A, and why
youtube-transcript 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 2d 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.
What it actually says
{
"name": "youtube-transcript",
"version": "0.1.1768936949",
"description": "Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.",
"author": {
"name": "Eleanor Berger",
"url": "https://intellectronica.net"
},
"repository": "https://github.com/intellectronica/agent-skills",
"homepage": "https://github.com/intellectronica/agent-skills/tree/main/plugins/youtube-transcript",
"license": "MIT"
}
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.
- 2d ago First seen · 13 lines scan A 4fc900b1ad03
youtube-transcript is a plugin published in the GitHub repository intellectronica/agent-skills (290 stars, last pushed 4mo ago), licensed CC0-1.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
xcode-build-skills
Plugin marketplace listing 1 plugin: xcode-build-skills.
xcode-build-skills
A multi-skill plugin for benchmarking and optimizing Xcode builds, compile hotspots, project settings, and Swift Package Manager dependency overhead.
mongodb-plugins
Plugin marketplace listing 2 plugins: mongodb, mongodb-atlas.
anycap
The AnyCap Agent Skills collection.
anycap
Multimodal capabilities for AI agents through the AnyCap CLI.
live-canvas-channel
Bridges the Live Canvas browser overlay to a Claude Code session. Each overlay Save becomes a claude/channel notification delivered over MCP.