Borrowing it
Nothing to install: this file belongs to Limecooler/yt-video-info. 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/Limecooler/yt-video-info/main/CLAUDE.mdgit clone --depth 1 https://github.com/Limecooler/yt-video-infoWrote 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/limecooler/yt-video-info/claude-md)<a href="https://agentmods.dev/instructions/limecooler/yt-video-info/claude-md"><img src="https://agentmods.dev/badge/instructions/limecooler/yt-video-info/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.
<a href="https://agentmods.dev/instructions/limecooler/yt-video-info/claude-md"><img src="https://agentmods.dev/badge/instructions/limecooler/yt-video-info/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01406 | $0.01406 |
| Opus 5.5 | $0.00562 | $0.00562 |
| Sonnet 5.5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
yt-video-info 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 2mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A lightweight MCP (Model Context Protocol) server that retrieves YouTube video information and transcripts using web scraping (no API keys required).
Common Commands
npm install- Install dependenciesnpm run build- Build TypeScript to JavaScriptnpm run dev- Run in development mode with auto-reloadnpm start- Run the MCP servernpx tsx src/index.ts- Run directly without building
Architecture
Core Components
-
MCP Server (
src/index.ts)- Implements a single tool:
get_video_info - Handles MCP protocol communication via stdio
- Returns video metadata and transcripts
- Uses Zod for runtime validation of tool arguments
- Implements a single tool:
-
Scraper Module (
src/scraper.ts)- Extracts video data from YouTube's web interface
- Parses
ytInitialPlayerResponsefrom HTML - Attempts to fetch transcripts in multiple formats (json3, srv3, vtt)
- Implements retry logic with exponential backoff
- Caches results for improved performance
-
Types (
src/types.ts)- TypeScript interfaces for video metadata, transcripts, and errors
- Custom error types with specific error codes
- Enhanced error codes: INVALID_ID, NOT_FOUND, PRIVATE, AGE_RESTRICTED, REGION_BLOCKED, NO_TRANSCRIPT, PARSE_ERROR, NETWORK_ERROR, RATE_LIMITED, TIMEOUT
-
Validation (
src/validation.ts)- Zod schemas for runtime type validation
- Validates video IDs, API responses, and transcript formats
- Provides clear error messages for invalid inputs
-
Utils (
src/utils.ts)- Retry logic with exponential backoff and jitter
- Helper functions for error handling
- Sleep utility for delays
-
Cache (
src/cache.ts)- In-memory LRU cache with TTL support
- Separate caches for video info (1 hour) and transcripts (2 hours)
- Automatic cleanup of expired entries
-
Logger (
src/logger.ts)- Debug logging to stderr (doesn't interfere with MCP)
- Controlled by MCP_DEBUG or DEBUG environment variables
- Log levels: debug, info, warn, error
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.
- 2mo ago First seen · 164 lines · 1,406 tokens per session scan A ed3587935623
yt-video-info CLAUDE.md is an instructions file published in the GitHub repository Limecooler/yt-video-info (1 stars, last pushed 1y ago), licensed MIT. It adds 1,406 tokens to every session, about $0.0056 per session on Opus 5.5. 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.
yt-video-info CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yt-video-info CLAUDE.mdLimecooler/yt-video-info | Instructions file | 1 | 1y ago | MIT | A | 1,406 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |