agentmods.dev

mvf1 CLAUDE.md

mvf1 CLAUDE.md is an instructions file for coding agents from RobSpectre/mvf1. It costs 613 tokens per session, scanned A, original, MIT.

Project instructions for mvf1, a Python package and command-line tool that controls MultiViewer video players. MultiViewer is a desktop application for watching Formula 1 and other motorsports with several synchronized video streams.

In plain words
What is it for?
Developing the Python library, command-line commands, or Model Context Protocol server used to list, create, delete, and control MultiViewer players.
Why use it?
They give an agent the project’s architecture and conventions so it can make changes in the right parts of the code. They also explain that control happens through a local GraphQL interface.

Instructions file

not rated 19 6d ago A scan 613 tokens original MIT
View the source file RobSpectre/mvf1
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/robspectre/mvf1/claude-md
Clone the repo
git clone --depth 1 https://github.com/RobSpectre/mvf1

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 mvf1 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robspectre/mvf1/claude-md.svg)](https://agentmods.dev/instructions/robspectre/mvf1/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/robspectre/mvf1/claude-md"><img src="https://agentmods.dev/badge/instructions/robspectre/mvf1/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 613 This file is loaded in full into every session.
When invoked 613 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00613 $0.00613
Opus 5 $0.00307 $0.00307
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00061 $0.00061

Measured 5d ago against content hash 914ac955a8bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mvf1 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 5d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 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

This is mvf1 - a Python package, command line interface, and MCP (Model Context Protocol) server for controlling MultiViewer video players. MultiViewer is a desktop application for watching Formula 1 and other motorsports with multiple synchronized video streams.

Key Architecture

Core Components

  • mvf1/mvf1.py: Main library with MultiViewerForF1 class and Player class

    • MultiViewerForF1: Primary interface for controlling MultiViewer via GraphQL API (localhost:10101)
    • Player: Represents individual video players with methods for control (pause, mute, seek, etc.)
    • Communicates with MultiViewer desktop app via GraphQL at http://localhost:10101/api/graphql

  • mvf1/mcp.py: FastMCP server implementation exposing MultiViewer controls as MCP tools

    • Provides AI agents with tools to control video players
    • Tools include: f1_live_timing_state(), players(), player_create(), player_delete(), etc.

  • mvf1/cmdline.py: Click-based CLI with two main command groups

    • players: Control all players (list, close, mute, pause, sync)
    • player: Control specific player by ID or title

  • mvf1/mvf1_schema.py: Auto-generated GraphQL schema definitions using sgqlc

Key Features

  • Player Management: Create, delete, control individual video players
  • Live Timing Integration: Access F1 and WEC live timing data
  • Synchronization: Sync all players to commentary or specific player timestamp
  • MCP Integration: Expose functionality to AI agents via Model Context Protocol

Development Commands

Testing

# Run all tests across Python versions
tox

# Run tests with coverage
pytest --cov=./

Installation

# Install in development mode
pip install -e ./

CLI Usage

# List all active players
mvf1-cli players ls

# Run MCP server with default URL
mvf1-cli mcp

# Run MCP server with custom URL
mvf1-cli mcp --url http://192.168.1.100:10101/api/graphql

Read the full file on GitHub · 75 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. 5d ago First seen · 75 lines · 613 tokens per session scan A 914ac955a8bd

Subscribe to this mod's changes

mvf1 CLAUDE.md is an instructions file published in the GitHub repository RobSpectre/mvf1 (19 stars, last pushed 6d ago), licensed MIT. It adds 613 tokens to every session, about $0.0031 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.

LanguagesPython
Related

Other instructions, from other repositories

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

technocore-chat AGENTS.md

AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.

flop-labs/technocore-chat · 621 tokens

foundry-local python-cffi-pointer-types.instructions.md

Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.

microsoft/foundry-local · 798 tokens

haggle AGENTS.md

AGENTS.md instructions for NaanyaBiz/haggle, covering agents.md — haggle integration guide, dev loop, install deps (once, or after pyproject.toml changes), run tests and lint + format.

NaanyaBiz/haggle · 15,728 tokens

pydantic-ai-gepa AGENTS.md

AGENTS.md instructions for indexedlabs/pydantic-ai-gepa, covering repository guidelines, mighty workflow, project structure & module organization, build, test, and development commands and coding style & naming conventions.

indexedlabs/pydantic-ai-gepa · 636 tokens

genmedia-izumi-agent GEMINI.md

Gemini CLI instructions for GoogleCloudPlatform/genmedia-izumi-agent.

GoogleCloudPlatform/genmedia-izumi-agent · 147 tokens