Borrowing it
Nothing to install: this file belongs to ssimonitch/mcp-pyboy. 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/ssimonitch/mcp-pyboy/main/CLAUDE.mdgit clone --depth 1 https://github.com/ssimonitch/mcp-pyboyWrote 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/ssimonitch/mcp-pyboy/claude-md)<a href="https://agentmods.dev/instructions/ssimonitch/mcp-pyboy/claude-md"><img src="https://agentmods.dev/badge/instructions/ssimonitch/mcp-pyboy/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 | $0.01606 | $0.01606 |
| Opus 5 | $0.00803 | $0.00803 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
mcp-pyboy 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 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP PyBoy Project Instructions
Overview
MCP server for Game Boy emulation via PyBoy, designed for LLM interaction.
Development Environment
This project uses uv for fast Python dependency management.
Setup Commands
# Install all dependencies (creates .venv automatically)
uv sync
# Install with development dependencies
uv sync --extra dev
# Run commands in virtual environment
uv run <command>
# Activate virtual environment manually (optional)
source .venv/bin/activate
Key Conventions
- All async functions use type hints
- Docstrings follow Google style
- Error messages include recovery suggestions
- Tests use pytest with async support
- Python 3.10+ required
Common Tasks
- Run tests:
uv run test(oruv run pytest tests/ -v) - Format code:
uv run format(oruv run black src/ tests/) - Type check:
uv run typecheck(oruv run mypy src/) - Lint code:
uv run lint(oruv run ruff check src/ tests/) - Start MCP server:
uv run python src/mcp_server/server.py - Test MCP server:
uv run mcp dev src/mcp_server/server.py(development mode) - Install for Claude Desktop:
uv run mcp install src/mcp_server/server.py --name "PyBoy Dev" - Start web API server:
uv run web-server(oruv run python src/web_server/app.py) - Install new dependency:
uv add <package-name> - Install dev dependency:
uv add --dev <package-name>
Architecture Notes
MCP Server Design
- Uses FastMCP for high-level MCP protocol handling
- Tools exposed via stdio transport for LLM integration
- Async/await patterns throughout for emulator interaction
- LLM-friendly error messages with recovery suggestions
Game Session Management
- Single PyBoy instance per session (singleton pattern)
- Input commands queued to prevent race conditions
- Screen captures cached to reduce CPU usage
- Session state persists across tool calls
Notebook System
- Game-specific notebooks (one per ROM, identified by hash)
- Focused on objectives, progress, and non-obvious discoveries
- Size limits per section to prevent bloat
- Automatic validation against redundant information
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 · 202 lines · 1,606 tokens per session scan A 0f143a83b402
mcp-pyboy CLAUDE.md is an instructions file published in the GitHub repository ssimonitch/mcp-pyboy (1 stars, last pushed 1y ago), licensed MIT. It adds 1,606 tokens to every session, about $0.0080 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
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.