Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add JCodesMore/youtube-for-ai-agents/plugin install youtubeWrote 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/jcodesmore/youtube-for-ai-agents/setup)<a href="https://agentmods.dev/skills/jcodesmore/youtube-for-ai-agents/setup"><img src="https://agentmods.dev/badge/skills/jcodesmore/youtube-for-ai-agents/setup.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.02375 |
| Opus 5 | $0.00014 | $0.01188 |
| Sonnet 5 | $0.00005 | $0.00475 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
youtube:setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Plugin Setup
A guided walkthrough for configuring how the YouTube plugin works. Present this as a friendly, conversational experience.
Step 1 — Check Current State
Run silently (don't show raw output to the user):
node "${CLAUDE_PLUGIN_ROOT}/scripts/extract-cookies.mjs" --status
node "${CLAUDE_PLUGIN_ROOT}/scripts/config.mjs" --show
Determine the current auth mode:
- "No cookies configured" → currently anonymous
- "Authenticated" → currently personalized
- "Cookie file exists but appears invalid" → broken state, treat as anonymous
Store both the auth state and config output for use in the next step.
Step 2 — Present the Welcome and Options
Greet the user and present the available options. Tailor based on current state. Always include the Configure settings option.
If currently anonymous:
Present this to the user (use your own natural phrasing, but cover these points):
YouTube Plugin Setup
The YouTube plugin has two modes:
Anonymous (current) — Ready to use right now. You get full access to search, transcripts, video info, and channel browsing. Results are based on general relevance.
Personalized — Connects to your YouTube account via a dedicated Chrome window. Search results will reflect your watch history, subscriptions, and preferences — just like searching on youtube.com when you're logged in.
What would you like to do?
- Keep anonymous — nothing to set up, you're good to go
- Set up personalized results — takes about a minute the first time
- Configure settings — customize search defaults, transcript language, result limits, and more
If currently personalized:
YouTube Plugin Setup
You're currently using personalized mode — search results reflect your YouTube account.
What would you like to do?
- Keep personalized — no changes needed
- Refresh cookies — if results seem off or you switched Google accounts
- Switch to anonymous — removes your cookies, uses general results instead
- Configure settings — customize search defaults, transcript language, result limits, and more
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.
- 6d ago First seen · 257 lines · 27 tokens per session scan A 56166f6f640a
youtube:setup is a skill published in the GitHub repository JCodesMore/youtube-for-ai-agents (50 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,375 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
plugin-init
初始化 Zhin.js 插件项目。Use when asked to create a new plugin, scaffold plugin structure, or set up a plugin project. 引导生成符合 Plugin Runtime 规范的目录结构、package.json、plugin.ts、约定能力目录和 README。.
plugin-publish
发布 Zhin.js 插件到 npm 和 Zhin 插件市场。Use when asked to publish a plugin, prepare for release, check publish readiness, or submit to the Zhin plugin marketplace. 引导完成发布前检查、版本管理和提交流程。.
plugin-develop
Implement Zhin.js plugin features with Plugin Runtime: defineCommand, defineAgentTool, middleware, pages. Use when asked to add a command, register a tool, wire cron, extend middleware, or build a console page. Triggers: 插件开发, add command, 加命令, 写插件功能, defineCommand.
commands-create-slash-command
Create or update Agent Zero slash commands for the built-in Commands plugin. Use when the user asks to add, edit, duplicate, or refine a reusable /command backed by YAML config plus text/python content files.
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
research-extraction
Deep extraction of research corpora into structured knowledge documents using a Workflow-driven subagent/reviewer pattern. Use when you have raw source documents (theses, papers, reports) and need structured extraction across multiple axes (architecture, messages, algorithms, forms, etc.) with confidence-annotated…