Borrowing it
Nothing to install: this file belongs to BlaiseMoses01/playback-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/BlaiseMoses01/playback-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/BlaiseMoses01/playback-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/blaisemoses01/playback-mcp/claude-md)<a href="https://agentmods.dev/instructions/blaisemoses01/playback-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/blaisemoses01/playback-mcp/claude-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 | $0.01252 | $0.01252 |
| Opus 5 | $0.00626 | $0.00626 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
playback-mcp 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 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 — 88 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.
What this is
A local-first system for controlling browser video playback from MCP clients. Many Claude
sessions can run at once: each playback-mcp process connects to a shared broker daemon
that owns the localhost port, and each session (identified by a sessionId) drives its own
YouTube tab, so sessions play different videos in parallel.
Claude A ──stdio──▶ playback-mcp(sess A) ─┐ ┌─ tab A ──▶ <video X>
Claude B ──stdio──▶ playback-mcp(sess B) ─┼─▶ broker (ws://127.0.0.1:8765) ─▶ extension ─┼─ tab B ──▶ <video Y>
Claude C ──stdio──▶ playback-mcp(sess C) ─┘ └─ tab C ──▶ <video Z>
It's a pnpm workspace monorepo (server + extension); ESM throughout. Run all
tooling from the repo root.
server/— the MCP server workspace (package name:playback-mcp). Node ≥ 23.4 (uses the built-innode:sqlite).extension/— the Chrome extension workspace, bundled with esbuild and loaded unpacked fromextension/distduring development.
Commands
pnpm install # install both workspaces (husky hooks install via prepare)
pnpm run build # build server (tsc) + extension (esbuild) across workspaces
pnpm run lint # eslint over the whole repo
pnpm run format # prettier --write (format:check for the CI-style check)
pnpm run typecheck # tsc --noEmit for server + extension tsconfigs
pnpm test # vitest run (server pure-logic tests)
pnpm run smoke # E2E over real MCP stdio, no browser needed
Architecture
server/src/
index.ts # MCP server entry (bin: playback-mcp) — registers tools over stdio
broker.ts # standalone daemon (bin: playback-mcp-broker) that owns the localhost port
# and multiplexes many servers onto the one extension, routing by sessionId
bridge.ts # session-tagged WebSocket client to the broker (auto-spawns it if not running)
db.ts # saved-video library on top of node:sqlite (shared WAL DB across servers)
timeparse.ts # pure: parse/format times, rates, volumes from agent-supplied strings
transcript.ts # pure: normalize/format/search caption payloads (unit-tested)
captions.ts # fetches captions from YouTube (innertube ANDROID /player → timedtext json3)
tools/ # MCP tool implementations (playback, library, loop, sequence, transcript, util)
extension/src/
background.ts # service worker: WS client to the broker; keeps a managed tab per sessionId
content.ts # content script: drives the page's <video> element (one instance per tab)
esbuild.mjs # bundles to IIFE for Chrome; reads __WS_PORT__ at build time
scripts/
mcp-poke.mjs # smoke test: spawns the broker + two servers + a fake extension over stdio
fake-extension.mjs
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 · 88 lines · 1,252 tokens per session scan A 2ddd302da7bc
playback-mcp CLAUDE.md is an instructions file published in the GitHub repository BlaiseMoses01/playback-mcp (5 stars, last pushed 7d ago), licensed MIT. It adds 1,252 tokens to every session, about $0.0063 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.