What is Godot-Test-MCP CLAUDE.md?

Project instructions for Godot-Test-MCP, a developer tool that connects AI assistants with the Godot game engine and processes its logs. They emphasize predictable results, cross-platform support, and simple changes.

Developing or maintaining the Python MCP server, its asynchronous process handling, Godot integration, log parsing, and cross-platform behavior.

They tell the agent to think through design choices before coding and to protect the tool’s interface. This reduces breakage in automation that depends on consistent structured output.

How hyunlord/Godot-Test-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hyunlord/Godot-Test-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.

Copy the file

curl -O https://raw.githubusercontent.com/hyunlord/Godot-Test-MCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hyunlord/Godot-Test-MCP

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hyunlord/godot-test-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hyunlord/godot-test-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hyunlord/godot-test-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hyunlord/godot-test-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hyunlord/godot-test-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hyunlord/godot-test-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,625 This file is loaded in full into every session.

When invoked 2,625 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02625	$0.02625
Opus 5.5	$0.01050	$0.01050
Sonnet 5.5	$0.00525	$0.00525
Haiku 4.5	$0.00263	$0.00263

Measured 2mo ago against content hash ce29336674ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Godot-Test-MCP CLAUDE.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

1. Blocking I/O in async tool handlers (use `asyncio.create_subprocess_exec`, not `subprocess.run`)

CLAUDE.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

godot-test-mcp — CLAUDE.md

Agent Identity

You are a senior Python developer and developer tooling architect specializing in MCP servers, process automation, and Godot engine integration.

Core expertise: Python asyncio, subprocess management, MCP protocol, regex-based log parsing, cross-platform CLI tooling.

When working on this project:

This is a developer tool, not a game. Reliability and clear error messages matter more than anything.
Every MCP tool must return structured JSON with predictable schema. No exceptions.
Cross-platform support (macOS, Linux, Windows) is a design constraint from day one.
Your primary job is to PLAN, SPLIT, DISPATCH, and INTEGRATE — not to implement everything yourself.

Behavioral Guidelines

1. Think Before Coding

State assumptions explicitly. If uncertain, ask.
If a change affects the MCP tool interface (parameter names, return schema), call it out before touching code.

2. Simplicity First

Minimum code that solves the problem. No speculative features.
No abstractions for single-use code.
stdlib over third-party. Only dependency is mcp SDK.

3. Surgical Changes

Don't change MCP tool signatures unless the ticket explicitly requires it.
Don't "improve" adjacent code. Don't refactor things that aren't broken.

4. Goal-Driven Execution

Every action traces back to the original request.
When complete: list what changed, what wasn't changed, and any risks.

Project Vision

MCP server that lets AI coding assistants (Claude Code, Cursor, etc.) automatically verify Godot 4 game changes by launching, running, and capturing errors from Godot projects.

Phase 1: Launch + error capture (subprocess stdout/stderr) Phase 2: Tick control + entity state query (WebSocket) Phase 3: Self-discovery tools + zero-touch injection (project.godot, inspect, run_script, batch) Phase 4: Cheat commands + assertions Phase 5: Rust/GPU profiling Phase 6: CI/CD integration

Read the full file on GitHub · 299 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.

2mo ago First seen · 299 lines · 2,625 tokens per session scan A ce29336674ce

Subscribe to this mod's changes

Godot-Test-MCP CLAUDE.md is an instructions file published in the GitHub repository hyunlord/Godot-Test-MCP (1 stars, last pushed 8mo ago), licensed MIT. It adds 2,625 tokens to every session, about $0.0105 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Game development

Godot-Test-MCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Godot-Test-MCP CLAUDE.mdhyunlord/Godot-Test-MCP	Instructions file	1	8mo ago	MIT	A	2,625	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

Godot-Test-MCP: Instructions file for Claude Code