What is Ultra-Godot-MCP-ASL AGENTS.md?

A set of instructions for specialized assistants that work with Godot Engine projects through a Python MCP server. It covers tasks such as reading Godot scene files, editing arrays, using code diagnostics, and debugging.

Use it when working on Godot scenes, GDScript, resources, code completion, diagnostics, breakpoints, generated scripts, or MCP server extensions.

It helps an AI agent choose the right specialist for different Godot development tasks instead of handling every task the same way.

How CerebroCanibalus/Ultra-Godot-MCP-ASL configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to CerebroCanibalus/Ultra-Godot-MCP-ASL. 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/CerebroCanibalus/Ultra-Godot-MCP-ASL/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/CerebroCanibalus/Ultra-Godot-MCP-ASL

Made for: Codex, OpenCode.

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/cerebrocanibalus/ultra-godot-mcp-asl/agents-md/github.svg)](https://agentmods.dev/instructions/cerebrocanibalus/ultra-godot-mcp-asl/agents-md)

Your own site

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

Per session 4,894 This file is loaded in full into every session.

When invoked 4,894 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.04894	$0.04894
Opus 5.5	$0.01958	$0.01958
Sonnet 5.5	$0.00979	$0.00979
Haiku 4.5	$0.00489	$0.00489

Measured 2mo ago against content hash f61d3b573065, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ultra-Godot-MCP-ASL AGENTS.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.

AGENTS.md · 710 lines

How it starts

The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Subagentes del MCP Godot Python

Este documento define los subagentes especializados para el MCP Godot Python, un servidor que permite a LLMs interagir con proyectos Godot Engine.

📋 Subagentes Disponibles

Agente	Descripción	Propósito Principal
`@Parser`	Especialista en parsing TSCN y formatos Godot	Analizar y manipular archivos .tscn, .gd, .tres
`@ArrayOps`	Operaciones quirúrgicas sobre arrays	Añadir/quitar/modificar elementos sin reescribir archivos
`@LSPClient`	Language Server Protocol de Godot	Autocompletado, hover, diagnósticos de GDScript
`@DAPClient`	Debug Adapter Protocol de Godot	Debugging, breakpoints, stack traces
`@CacheMaster`	Gestión de cache LRU e invalidación	Optimizar operaciones repetitivas
`@TemplateEngine`	Templates Jinja2 para nodos/scripts	Generar código GDScript automáticamente
`@ToolSmith`	Creación de herramientas FastMCP	Extender funcionalidades del servidor
`@SessionKeeper`	Gestión de sesiones ligeras	Manejar conexiones temporales
`@GodotSage`	Conocimiento profundo de Godot Engine	Consulta de documentación y mejores prácticas

🎯 @Parser - Especialista en Parsing TSCN

Responsabilidades

Parsear archivos .tscn (formato de escena Godot)
Parsear archivos .gd (scripts GDScript)
Parsear archivos .tres (recursos Godot)
Analizar estructura de nodos
Validar sintaxis y referencias
Extraer metadatos de recursos

Cuándo Invocarlo

Cuando necesitas analizar una escena existente
Al crear o modificar nodos en tiempo real
Para obtener información de recursos
Al validar referencias entre escenas

Herramientas MCP Usadas

# Herramientas principales del Parser
- mcp__godot__get_scene_tree    # Obtener jerarquía de nodos
- mcp__godot__list_scenes     # Listar todas las escenas
- mcp__godot__find_nodes     # Buscar nodos por tipo
- mcp__godot__get_node_properties  # Propiedades de un nodo

Read the full file on GitHub · 710 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 · 710 lines · 4,894 tokens per session scan A f61d3b573065

Subscribe to this mod's changes

Ultra-Godot-MCP-ASL AGENTS.md is an instructions file published in the GitHub repository CerebroCanibalus/Ultra-Godot-MCP-ASL (25 stars, last pushed 6mo ago), licensed MIT. It adds 4,894 tokens to every session, about $0.0196 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 2026-08-30.

Game development

Ultra-Godot-MCP-ASL AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Ultra-Godot-MCP-ASL AGENTS.mdCerebroCanibalus/Ultra-Godot-MCP-ASL	Instructions file	25	6mo ago	MIT	A	4,894	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Ultra-Godot-MCP-ASL: Instructions file for Codex