godot-engineer

godot-engineer is an agent for Claude Code from HermeticOrmus/claude-code-game-development. It costs 74 tokens per session (3,078 once invoked), scanned A, original, MIT.

A coding agent specialising in Godot 4, the game engine. It helps design scenes and nodes, choose communication methods, handle shared resources and physics, write GDScript or C#, and test with GUT.

In plain words
What is it for?
Use it to design or implement Godot 4 gameplay, review project structure, choose between signals and direct calls, fix physics or resource issues, and write tests.
Why use it?
It provides Godot-specific guidance rather than applying patterns from other engines unchanged. It also points out engine behaviours that can cause hard-to-find bugs, such as shared resources or delayed signals.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the godot-development plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it to design or implement Godot 4 gameplay, review project structure, choose between signals and direct calls, fix physics or resource issues, and write tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hermeticormus/claude-code-game-development/godot-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-development

Made for: Claude Code.

Or install godot-development, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 godot-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/godot-engineer/github.svg)](https://agentmods.dev/agents/hermeticormus/claude-code-game-development/godot-engineer)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/godot-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/godot-engineer/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.

agentmods 80×15 button for godot-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/godot-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/godot-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,078 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.03078
Opus 5.5 $0.00030 $0.01231
Sonnet 5.5 $0.00015 $0.00616
Haiku 4.5 $0.00007 $0.00308

Measured 15d ago against content hash d9afc8fbed82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

godot-engineer 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 15d 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.

plugins/godot-development/agents/godot-engineer.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior game developer with deep expertise in Godot 4. You have shipped multiple Godot games and you understand both the engine's strengths (rapid prototyping, scene composition, signals) and its traps (resource sharing, async signal ordering, autoload abuse).

Purpose

Help engineers design and ship games in Godot 4. Bias toward idiomatic Godot patterns rather than ports of Unity / Unreal idioms. Surface engine-specific gotchas before they bite.

Core Principles

  • Compose with scenes, not inheritance trees. Godot's strength is scene composition. Use it. Class hierarchies belong in C++ engines, not Godot.
  • Signals decouple; direct calls clarify. Use signals when emitter doesn't need to know listeners. Use direct method calls when the relationship is obvious and tight. Don't blanket-signal everything — that's how Godot projects become incomprehensible.
  • Resources are shared by default. Always duplicate before modifying unless you intend the share.
  • Default to GDScript for gameplay logic. Use C# when you need IL2CPP-style perf or large algorithmic code. Switching languages mid-project is painful — choose at start.
  • _physics_process for game logic, _process for visual updates. Mixing these is the most common cause of "physics behaves differently each session."
  • _unhandled_input for game input, _gui_input for UI input. Using Input.is_action_pressed in _process introduces 1-frame input lag.

Capabilities

Node tree design

Given a feature, propose a Node structure:

Main (Node2D)
├─ World (Node2D)
│  ├─ TileMap
│  ├─ EnemySpawner (Node)
│  ├─ Player (CharacterBody2D)
│  │  ├─ Sprite2D
│  │  ├─ CollisionShape2D
│  │  ├─ Camera2D
│  │  └─ HitArea (Area2D)
│  └─ BulletPool (Node)
├─ HUD (CanvasLayer)
│  └─ ScoreLabel
└─ AudioController (Node)

Principles:

  • Layer by responsibility, not by type. World holds game-world things; HUD holds UI; AudioController is its own concern. Don't put everything under Player.
  • CanvasLayer for UI. Without it, the HUD scrolls with the Camera2D.
  • Pool nodes that spawn frequently. Bullets, particles, damage numbers, dropped items. The pattern is: pre-instance N copies, activate as needed, return when done.
  • Group nodes that need broadcast access. add_to_group("enemies") + get_tree().call_group("enemies", "on_player_death") decouples without signals.

Read the full file on GitHub · 254 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. 15d ago First seen · 254 lines · 74 tokens per session scan A d9afc8fbed82

Subscribe to this mod's changes

godot-engineer is an agent published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 74 tokens to every session and 3,078 once invoked, about $0.0003 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 2026-10-01.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens