godot-4

godot-4 is a skill for Claude Code, Codex from medy-gribkov/arcana. It costs 30 tokens per session (3,944 once invoked), scanned A, original, Apache-2.0.

A development guide for making games with Godot 4, a game engine, using its GDScript 2.0 language. It covers scenes, physics, signals, and performance.

In plain words
What is it for?
Use it to build gameplay systems, compose scenes, handle physics and signals, and improve game performance.
Why use it?
It provides consistent patterns for organizing Godot projects and writing typed game code that works well with editor support.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is get_node("../UI/ScoreLabel").update_display().

Good fit Use it to build gameplay systems, compose scenes, handle physics and signals, and improve game performance.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/medy-gribkov/arcana
agentmods
npx agentmods add skills/medy-gribkov/arcana/godot-4

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin godot-4/plugin install godot-4 after adding the marketplace above.

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-4

README.md
[![agentmods](https://agentmods.dev/badge/skills/medy-gribkov/arcana/godot-4/github.svg)](https://agentmods.dev/skills/medy-gribkov/arcana/godot-4)
Your own site
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/godot-4"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/godot-4/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-4

Your own site · 80×15
<a href="https://agentmods.dev/skills/medy-gribkov/arcana/godot-4"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/godot-4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,944 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 $0.00030 $0.03944
Opus 5 $0.00015 $0.01972
Sonnet 5 $0.00006 $0.00789
Haiku 4.5 $0.00003 $0.00394

Measured 11d ago against content hash 7f401c886309, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

godot-4 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 11d 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.

skills/godot-4/SKILL.md · 635 lines

How it starts

The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot 4 Development Skill

Expert guidance for Godot 4 game development using GDScript 2.0, scene composition, physics systems, and performance optimization.

GDScript 2.0 Typed Syntax

Always use static typing for performance and IDE support.

BAD: Untyped variables and functions

var health = 100
var player
var enemies = []

func take_damage(amount):
    health -= amount
    return health <= 0

GOOD: Fully typed with explicit return types

var health: int = 100
var player: CharacterBody2D
var enemies: Array[Enemy] = []

func take_damage(amount: int) -> bool:
    health -= amount
    return health <= 0

@export and @onready Patterns

Use typed @export for inspector values and @onready for node references.

BAD: Untyped exports, get_node in _ready

@export var speed = 300
@export var jump_force = -400

var sprite
var collision

func _ready():
    sprite = get_node("Sprite2D")
    collision = get_node("CollisionShape2D")

GOOD: Typed exports with hints, @onready with type annotations

@export_range(100, 500, 10) var speed: float = 300.0
@export_range(-800, -200, 50) var jump_force: float = -400.0
@export var gravity: float = 980.0

@onready var sprite: Sprite2D = $Sprite2D
@onready var collision: CollisionShape2D = $CollisionShape2D
@onready var animation: AnimationPlayer = $AnimationPlayer

Scene Composition and Node Architecture

Structure games as composable scenes, not monolithic scripts.

BAD: Monolithic player script handling everything

extends CharacterBody2D

var health = 100
var ammo = 30
var inventory = []

func _process(delta):
    update_health_bar()
    update_ammo_display()
    update_inventory_ui()
    check_pickups()
    handle_combat()

GOOD: Component-based scene composition

# Player.gd
extends CharacterBody2D
class_name Player

@onready var health_component: HealthComponent = $HealthComponent
@onready var inventory_component: InventoryComponent = $InventoryComponent
@onready var weapon_component: WeaponComponent = $WeaponComponent

func _ready() -> void:
    health_component.died.connect(_on_died)
    weapon_component.fired.connect(_on_weapon_fired)

func _on_died() -> void:
    animation.play("death")
    set_physics_process(false)

Read the full file on GitHub · 635 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. 11d ago First seen · 635 lines · 30 tokens per session scan A 7f401c886309

Subscribe to this mod's changes

godot-4 is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,944 once invoked, about $0.0002 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.