Borrowing it
Nothing to install: this file belongs to kirbah/mcp-youtube. 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/kirbah/mcp-youtube/main/AGENTS.mdgit clone --depth 1 https://github.com/kirbah/mcp-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/instructions/kirbah/mcp-youtube/agents-md)<a href="https://agentmods.dev/instructions/kirbah/mcp-youtube/agents-md"><img src="https://agentmods.dev/badge/instructions/kirbah/mcp-youtube/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 | $0.01354 | $0.01354 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
mcp-youtube 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides instructions for AI coding agents on how to work with this project.
Project Philosophy
- Token Efficiency is Paramount: Every tool and data structure is designed to be "lean" and "token-optimized." When modifying code, prioritize returning only the most essential data to minimize the token footprint for the client LLM. Avoid verbose responses.
- LLM-Centric Design: Data should be structured for easy consumption by AI models. This means clear, predictable JSON structures and concise field names.
- Robustness and Reliability: All new code should include strong input validation (using Zod schemas) and clear, consistent error handling.
Key Commands
| Command | Description |
|---|---|
npm install |
Installs all project dependencies. Run this first. |
npm run lint |
Checks the code for linting errors according to ESLint rules. |
npm run format |
Automatically formats all code using Prettier. |
npm run test |
Executes the entire Jest test suite. All tests must pass before committing. |
npm run build |
Compiles the TypeScript project into JavaScript in the /dist directory. |
npm run inspector |
Runs the MCP server with a local inspector for debugging tools. |
Project Architecture
- Entry Point:
src/index.tsinitializes the environment, the service container, and the MCP server. It registers all tools. - Dependency Injection:
src/container.tsmanages singleton instances of core services. When you need access to a service within a tool handler, it is injected viasrc/tools/index.ts. - Services (
src/services/):YoutubeService: The main interface to the YouTube Data API. Contains all logic for fetching and transforming data. Most modifications to data fetching will happen here.CacheService: Provides a caching layer over MongoDB to reduce API calls and quota usage. TheYoutubeServiceuses this extensively.TranscriptService: Handles fetching and parsing video transcripts.
- Tools (
src/tools/): Each tool is defined in its own file and has three parts: a Zod schema for input validation, a configuration object (...Config), and a handler function (...Handler). - Tool Registration:
src/tools/index.tsis the central registry. All new tools must be added to theallToolsarray here to be exposed by the server.
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.
- 8d ago First seen · 83 lines · 1,354 tokens per session scan A f0a08bce258b
mcp-youtube AGENTS.md is an instructions file published in the GitHub repository kirbah/mcp-youtube (29 stars, last pushed 4d ago), licensed MIT. It adds 1,354 tokens to every session, about $0.0068 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 instructions, from other repositories
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).
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.
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.
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).
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.