agentmods.dev

youtube-for-ai-agents: Instructions file for Claude Code

CLAUDE.md

youtube-for-ai-agents CLAUDE.md is an instructions file for Claude Code from JCodesMore/youtube-for-ai-agents. It costs 906 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for YouTube for AI Agents, an MCP plugin that gives coding agents access to YouTube-related tools. It covers the TypeScript structure, configuration, transcripts, cookies, building, and distribution.

In plain words
What is it for?
Use it when changing YouTube tool handlers, transcript or authentication code, configuration, build scripts, or plugin distribution files.
Why use it?
It explains how the plugin is organized and reminds developers to keep its compiled files ready for marketplace installation.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

This is JCodesMore/youtube-for-ai-agents's own configuration. It tells Claude Code how to work on youtube-for-ai-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything youtube-for-ai-agents configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 50repo 4mo ago A scan 906 tokens original Apache-2.0
View source ↗ JCodesMore/youtube-for-ai-agents dsc.gg
Reuse

Borrowing it

Nothing to install: this file belongs to JCodesMore/youtube-for-ai-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/JCodesMore/youtube-for-ai-agents/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/JCodesMore/youtube-for-ai-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for youtube-for-ai-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jcodesmore/youtube-for-ai-agents/claude-md/github.svg)](https://agentmods.dev/instructions/jcodesmore/youtube-for-ai-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jcodesmore/youtube-for-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/jcodesmore/youtube-for-ai-agents/claude-md/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.

agentmods 80×15 button for youtube-for-ai-agents CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jcodesmore/youtube-for-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/jcodesmore/youtube-for-ai-agents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 906 This file is loaded in full into every session.
When invoked 906 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00906 $0.00906
Opus 5 $0.00453 $0.00453
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00091 $0.00091

Measured 9d ago against content hash aa9eb65de2a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

youtube-for-ai-agents CLAUDE.md 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 9d 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube for AI Agents

MCP plugin providing YouTube tools for AI coding agents. Supports Claude Code, Cursor, Codex, OpenCode, and Gemini CLI.

Architecture

src/index.ts          — Entry point. Registers 6 MCP tools, connects via stdio transport.
src/config.ts         — DEFAULTS object with all configurable settings and types.
src/tools/*.ts        — Tool handlers. Each exports inputSchema (zod) + handler function.
src/lib/innertube.ts  — Singleton YouTube API wrapper using youtubei.js.
src/lib/transcript.ts — Transcript fetching, HTML entity decoding, text cleanup.
src/lib/cookies.ts    — Cookie load/save/validate/delete for auth.
src/lib/user-config.ts — User config overrides, deep merge with defaults.

Build

Always run npm run build after changing any file in src/. The compiled output goes to dist/ and is committed to git (required for plugin marketplace distribution).

npm run build    # compile once
npm run dev      # watch mode

Plugin Distribution

When installed via marketplace (git clone), the plugin needs:

  • dist/ committed to git — Claude Code doesn't run build steps after cloning.
  • SessionStart hook (scripts/ensure-deps.mjs) — auto-installs runtime dependencies into the plugin root (next to dist/) on first session. Uses SHA-256 hash of package.json to skip on subsequent sessions. Deps install into CLAUDE_PLUGIN_ROOT (not CLAUDE_PLUGIN_DATA) because NODE_PATH does not work with ES modules — ESM resolution requires node_modules in the directory tree above the importing file.

On every version bump: run npm run build, commit dist/, push to GitHub, run npm publish, and update the version in JCodesMore/jcodesmore-plugins marketplace.json. Git and npm must stay in sync.

Key Patterns

  • Zod schemas define all tool inputs. Each tool file exports fooInputSchema and handleFoo.
  • InnerTube singleton (src/lib/innertube.ts) — lazy-initialized, tracks auth state (personalized vs anonymous).
  • getConfig() (src/lib/user-config.ts) — merges user overrides from .config.json with DEFAULTS from config.ts.
  • All tools are read-only — annotated with readOnlyHint: true, destructiveHint: false.

Read the full file on GitHub · 76 lines

Changes

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.

  1. 9d ago First seen · 76 lines · 906 tokens per session scan A aa9eb65de2a1

Subscribe to this mod's changes

youtube-for-ai-agents CLAUDE.md is an instructions file published in the GitHub repository JCodesMore/youtube-for-ai-agents (50 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 906 tokens to every session, about $0.0045 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.

Claude Codeagentaiclaudemcpplugin
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens