Borrowing it
Nothing to install: this file belongs to CreatorGeetansh/YouTube-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CreatorGeetansh/YouTube-MCP/main/AGENTS.mdgit clone --depth 1 https://github.com/CreatorGeetansh/YouTube-MCPWrote 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/instructions/creatorgeetansh/youtube-mcp/agents-md)<a href="https://agentmods.dev/instructions/creatorgeetansh/youtube-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/creatorgeetansh/youtube-mcp/agents-md.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 | $0.03240 | $0.03240 |
| Opus 5 | $0.01620 | $0.01620 |
| Sonnet 5 | $0.00648 | $0.00648 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
YouTube-MCP AGENTS.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 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Instructions for Coding Agents
This file is the binding development contract for this repository. It is written for Claude Code and applies to every agent or contributor working here. Read PLAN.md and README.md before changing implementation files.
Mission
Implement a secure, local-first, open-source YouTube MCP server whose central workflow turns a structured song list into a reviewed YouTube playlist. Also provide useful YouTube read tools and full playlist management, while refusing writes elsewhere in the user's account.
The architecture in PLAN.md is approved. Do not widen product scope or weaken its safety model without an explicit maintainer decision recorded in the plan and changelog.
Current state
The repository starts as documentation only. Do not claim commands, tools, releases, or integrations work until their phase gate passes. Keep the README's project-status checklist accurate in the same change that completes a milestone.
Non-negotiable decisions
- TypeScript, ESM, strict mode, Node.js 20 or newer.
- npm package:
@youtube-mcp/server; binary:youtube-mcp. - Official MCP TypeScript SDK; local
stdioonly in v1. - Official YouTube Data API v3 and Google OAuth endpoints only.
- Direct typed REST wrappers with an explicit host/endpoint/method/parameter allowlist.
- Bring-your-own Desktop OAuth client. Never ship a shared client ID or secret.
- Authorization Code + PKCE (
S256), randomstate, and a random loopback port on127.0.0.1. - API key preferred for public reads; OAuth for account reads and playlist writes.
- One named profile per process, selected at startup.
- Native keychain by default; no silent plaintext OAuth-token fallback.
- SQLite plus an in-memory LRU; no Redis in v1.
- Playlist-only writes, despite the broader Google OAuth scope.
- Private-by-default new playlists.
- Preview before commit and a hard limit of 50 track/item changes.
- Exact-diff, expiring, one-time confirmation for destructive mutations.
- No arbitrary URL fetch, generic Google API tool, captions scraping, or embedded LLM.
- Logs go to
stderr; MCP protocol data alone goes tostdout. - Apache-2.0 release intent.
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 · 282 lines · 3,240 tokens per session scan A 40542fe6da4f
YouTube-MCP AGENTS.md is an instructions file published in the GitHub repository CreatorGeetansh/YouTube-MCP (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,240 tokens to every session, about $0.0162 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 2026-08-31.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.