Game Asset Generator
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
A skill your agent uses when creating a new Phaser 4 game instance or configuring GameConfig options.
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness game-setup-and-config --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .claude/skills/game-setup-and-config && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .claude/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-configType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness game-setup-and-config --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .agents/skills/game-setup-and-config && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .agents/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness game-setup-and-config --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .cursor/skills/game-setup-and-config && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .cursor/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/phaser/skills/game-setup-and-config--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness game-setup-and-config --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .gemini/skills/game-setup-and-config && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .gemini/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness game-setup-and-configInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .github/skills/game-setup-and-config && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .github/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill game-setup-and-config -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness game-setup-and-config --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/phaser/skills/game-setup-and-config .opencode/skills/game-setup-and-config && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "game-setup-and-config" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/game-setup-and-config into .opencode/skills/game-setup-and-config/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "game-setup-and-config", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
game-setup-and-configA skill your agent uses when creating a new Phaser 4 game instance or configuring GameConfig options.
Game Setup And Config is an agent skill from autonomous-ai/openharness. Use this skill when creating a new Phaser 4 game instance or configuring GameConfig options. Covers renderer selection, canvas setup, scaling, pixel art, FPS settings, boot sequence, and all config sub-objects. Triggers on: new Phaser.Game, GameConfig, game setup, renderer, pixel art, FPS.
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Game Development, covering Sprites and pixel art and 3D graphics and WebGL. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit cc4983e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
phaser.ioFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Game Setup And Config loads about 4.9k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 1,638 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 1,638 words, ~4,904 tokens.
.claude/skills/game-setup-and-config/SKILL.md (or your agent's skills folder).How to create a Phaser.Game instance with the right GameConfig options for renderer, scaling, pixel art, FPS, and canvas placement.
Key source paths: src/core/Game.js, src/core/Config.js, src/core/typedefs/GameConfig.js, src/const.js, src/scale/const/
Related skills: ../scenes/SKILL.md, ../loading-assets/SKILL.md, ../scale-and-responsive/SKILL.md
The simplest possible Phaser 4 game -- a single scene with the default 1024×768 canvas:
class MyScene extends Phaser.Scene {
preload() {
this.load.image('logo', 'assets/logo.png');
}
create() {
this.add.image(400, 300, 'logo');
}
}
const config = {
type: Phaser.AUTO,
scene: MyScene
};
const game = new Phaser.Game(config);new Phaser.Game(config) triggers the entire boot sequence: config parsing (Config), renderer creation, DOM insertion, and the game loop (TimeStep). The game waits for DOMContentLoaded before booting.
new Phaser.Game(config) -- parses config into a Phaser.Core.Config instance.AnimationManager, TextureManager, CacheManager, InputManager, SceneManager, ScaleManager, SoundManager, TimeStep, PluginManager.DOMContentLoaded, then calls boot().boot() creates the renderer (CreateRenderer), adds the canvas to the DOM (AddToDOM), prints the debug header, emits BOOT.TextureManager emits READY), emits READY then calls start().start() begins the TimeStep loop, sets up the VisibilityHandler, calls config.postBoot.The Config constructor reads a flat GameConfig object and resolves defaults. Some properties can be specified at top level OR nested inside sub-objects (e.g., width can be top-level or under scale.width). The scale sub-object takes priority when both are present.
Render properties can likewise be top-level shortcuts (e.g., pixelArt: true) or nested under render.
| Constant | Value | Behavior |
|---|---|---|
Phaser.AUTO | 0 | WebGL if supported, else falls back to Canvas |
Phaser.CANVAS | 1 | Force Canvas renderer |
Phaser.WEBGL | 2 | Force WebGL -- no fallback if unsupported |
Phaser.HEADLESS | 3 | No renderer -- DOM still required. For unit testing only |
Set via config.type. Default is Phaser.AUTO.
When pixelArt is true, Config automatically sets antialias: false, antialiasGL: false, and roundPixels: true.
const config = {
type: Phaser.AUTO,
width: 320,
height: 240,
pixelArt: true,
scale: {
mode: Phaser.Scale.FIT,
autoCenter: Phaser.Scale.CENTER_BOTH,
zoom: Phaser.Scale.ZOOM_2X
},
scene: MyScene
};Preserves blocky pixels but smooths edges between them when scaled up:
const config = {
type: Phaser.WEBGL,
width: 320,
height: 240,
smoothPixelArt: true,
scene: MyScene
};When smoothPixelArt is true, Config sets antialias: true, antialiasGL: true, and pixelArt: false.
const config = {
type: Phaser.AUTO,
scale: {
mode: Phaser.Scale.RESIZE,
parent: 'game-container',
width: '100%',
height: '100%'
},
scene: MyScene
};const config = {
type: Phaser.AUTO,
scale: {
mode: Phaser.Scale.FIT,
parent: 'game-container',
autoCenter: Phaser.Scale.CENTER_BOTH,
width: 1280,
height: 720,
min: { width: 640, height: 360 },
max: { width: 1920, height: 1080 }
},
backgroundColor: '#2d2d2d',
scene: MyScene
};const config = {
type: Phaser.AUTO,
width: 800,
height: 600,
fps: {
target: 60,
limit: 30,
forceSetTimeOut: false,
smoothStep: true
},
scene: MyScene
};const config = {
type: Phaser.AUTO,
width: 800,
height: 600,
transparent: true,
parent: 'game-container',
scene: MyScene
};When transparent is true, backgroundColor is forced to 0x000000 with alpha 0.
const canvas = document.getElementById('my-canvas');
const config = {
type: Phaser.WEBGL,
canvas: canvas,
width: 800,
height: 600,
scene: MyScene
};const config = {
type: Phaser.AUTO,
width: 800,
height: 600,
scene: [BootScene, PreloadScene, MenuScene, GameScene],
physics: {
default: 'arcade',
arcade: { gravity: { y: 300 } }
}
};Only the first scene starts automatically. Others start only if they have { active: true } in their scene config. See ../scenes/SKILL.md.
const config = {
type: Phaser.AUTO,
width: 800,
height: 600,
callbacks: {
preBoot: function (game) {
// Runs before Phaser boots. Game systems not yet available.
},
postBoot: function (game) {
// Runs after boot. All systems ready, game loop starting.
}
},
scene: MyScene
};const config = {
type: Phaser.AUTO,
width: 800,
height: 600,
input: {
keyboard: true,
mouse: true,
touch: false,
gamepad: false,
activePointers: 1,
windowEvents: true
},
disableContextMenu: true,
scene: MyScene
};| Property | Type | Default | Description |
|---|---|---|---|
type | number | Phaser.AUTO (0) | Renderer: AUTO, CANVAS, WEBGL, or HEADLESS |
width | number|string | 1024 | Game width in pixels (or '100%'). Overridden by scale.width |
height | number|string | 768 | Game height in pixels (or '100%'). Overridden by scale.height |
zoom | number | 1 | Canvas zoom multiplier. Overridden by scale.zoom |
parent | HTMLElement|string|null | undefined | DOM element or id for canvas. undefined = document body. null = no parent |
canvas | HTMLCanvasElement | null | Provide your own canvas element |
context | CanvasRenderingContext2D|WebGLRenderingContext | null | Provide your own rendering context |
canvasStyle | string | null | CSS styles applied to the canvas element |
customEnvironment | boolean | false | Skip feature detection for non-browser environments. renderType cannot be AUTO if true |
scene | SceneType|SceneType[] | null | Scene class (extends Phaser.Scene) or array of scene classes |
seed | string[] | [random] | Seed for Phaser.Math.RND |
title | string | '' | Game title shown in console banner |
url | string | 'https://phaser.io/...' | Game URL shown in console banner |
version | string | '' | Game version shown in console banner |
autoFocus | boolean | true | Auto-focus window on boot and mousedown |
stableSort | number|boolean | -1 | -1 = auto-detect, 0/false = built-in stable sort, 1/true = rely on native ES2019 sort |
disableContextMenu | boolean | false | Disable right-click context menu |
backgroundColor | string|number | 0x000000 | Canvas background color. Accepts hex number, CSS string, or color object |
banner | boolean|BannerConfig | (shown) | false to hide console banner entirely |
| Property | Type | Default | Description |
|---|---|---|---|
width | number|string | 1024 | Base game width |
height | number|string | 768 | Base game height |
zoom | number | 1 | Zoom multiplier. Use constants: NO_ZOOM (1), ZOOM_2X (2), ZOOM_4X (4), MAX_ZOOM (-1) |
parent | HTMLElement|string | undefined | DOM parent for the canvas |
mode | number | Phaser.Scale.NONE (0) | Scale mode (see table below) |
expandParent | boolean | true | Allow adjusting parent CSS height to 100% |
autoRound | boolean | false | Round display/style sizes for performance |
autoCenter | number | NO_CENTER (0) | Canvas centering mode (see table below) |
resizeInterval | number | 500 | Milliseconds between browser size checks |
fullscreenTarget | HTMLElement|string | null | Element for fullscreen mode |
min | {width, height} | {0, 0} | Minimum canvas dimensions |
max | {width, height} | {0, 0} | Maximum canvas dimensions (0 = no limit) |
snap | {width, height} | {0, 0} | Snap canvas size to multiples |
| Constant | Value | Behavior |
|---|---|---|
Phaser.Scale.NONE | 0 | No scaling. Canvas stays at config size |
Phaser.Scale.WIDTH_CONTROLS_HEIGHT | 1 | Height adjusts based on width |
Phaser.Scale.HEIGHT_CONTROLS_WIDTH | 2 | Width adjusts based on height |
Phaser.Scale.FIT | 3 | Fit inside parent keeping aspect ratio (letterboxing) |
Phaser.Scale.ENVELOP | 4 | Cover parent keeping aspect ratio (may overflow) |
Phaser.Scale.RESIZE | 5 | Canvas resizes to fill parent, ignoring aspect ratio |
Phaser.Scale.EXPAND | 6 | Like RESIZE for visible area + FIT for canvas scale |
| Constant | Value |
|---|---|
Phaser.Scale.NO_CENTER | 0 |
Phaser.Scale.CENTER_BOTH | 1 |
Phaser.Scale.CENTER_HORIZONTALLY | 2 |
Phaser.Scale.CENTER_VERTICALLY | 3 |
| Constant | Value | Behavior |
|---|---|---|
Phaser.Scale.NO_ZOOM | 1 | No zoom |
Phaser.Scale.ZOOM_2X | 2 | 2x zoom |
Phaser.Scale.ZOOM_4X | 4 | 4x zoom |
Phaser.Scale.MAX_ZOOM | -1 | Max integer zoom that fits in parent |
These can be set at the top level OR nested under render. The render sub-object takes priority.
| Property | Type | Default | Description |
|---|---|---|---|
antialias | boolean | true | Linear interpolation for scaled/rotated textures |
antialiasGL | boolean | true | Antialias on WebGL context creation |
pixelArt | boolean | false | Sets antialias: false, roundPixels: true automatically |
smoothPixelArt | boolean | false | WebGL only. Blocky pixels with smooth edges |
roundPixels | boolean | false | Snap texture-based objects to integer positions |
transparent | boolean | false | Transparent canvas background |
clearBeforeRender | boolean | true | Clear canvas each frame |
preserveDrawingBuffer | boolean | false | Preserve WebGL buffers between frames |
premultipliedAlpha | boolean | true | Pre-multiplied alpha in WebGL drawing buffer |
desynchronized | boolean | false | Desynchronized rendering context |
failIfMajorPerformanceCaveat | boolean | false | Abort WebGL if browser reports poor performance |
powerPreference | string | 'default' | 'high-performance', 'low-power', or 'default' |
batchSize | number | 16384 | Max quads per WebGL batch |
maxTextures | number | -1 | Max GPU textures. -1 = use all available |
maxLights | number | 10 | Max lights visible per camera |
autoMobileTextures | boolean | true | Restrict to 1 texture per batch on iOS/Android |
selfShadow | boolean | false | Self-shadowing on lit textured objects |
pathDetailThreshold | number | 1 | Point-combining threshold for Graphics WebGL paths |
skipUnreadyShaders | boolean | false | Skip drawing objects whose shader is still compiling |
mipmapFilter | string | '' | Mipmap filter: 'NEAREST', 'LINEAR', 'NEAREST_MIPMAP_NEAREST', etc. |
renderNodes | object | {} | Custom render nodes for WebGL renderer |
| Property | Type | Default | Description |
|---|---|---|---|
min | number | 5 | Minimum acceptable FPS |
target | number | 60 | Target FPS (informational, does not enforce) |
limit | number | 0 | Enforce max FPS. 0 = no limit |
forceSetTimeOut | boolean | false | Use setTimeout instead of requestAnimationFrame |
deltaHistory | number | 10 | Frames to average for delta smoothing |
panicMax | number | 120 | Frames before trusting delta again after a panic |
smoothStep | boolean | true | Apply delta smoothing |
| Sub-Config Key | Type | Source |
|---|---|---|
callbacks | CallbacksConfig | src/core/typedefs/CallbacksConfig.js |
dom | DOMContainerConfig | src/core/typedefs/DOMContainerConfig.js |
input | InputConfig | src/core/typedefs/InputConfig.js |
loader | LoaderConfig | src/core/typedefs/LoaderConfig.js |
physics | PhysicsConfig | src/core/typedefs/PhysicsConfig.js |
plugins | PluginObject|PluginObjectItem[] | src/core/typedefs/PluginObject.js |
audio | AudioConfig | src/core/typedefs/AudioConfig.js |
images | ImagesConfig | src/core/typedefs/ImagesConfig.js |
Listen on game.events (or this.game.events from a Scene) for visibility and focus changes:
game.events.on('blur', () => { /* tab lost focus */ });
game.events.on('focus', () => { /* tab regained focus */ });
game.events.on('hidden', () => { /* Page Visibility API: page hidden */ });
game.events.on('visible', () => { /* Page Visibility API: page visible */ });
game.events.on('pause', () => { /* game.pause() was called */ });
game.events.on('resume', () => { /* game.resume() was called */ });Use named constants: Phaser.Core.Events.BLUR, FOCUS, HIDDEN, VISIBLE, PAUSE, RESUME.
// Pause the entire game loop (rendering and updates stop)
game.pause();
// Resume the game loop
game.resume();
// Check if the game is currently paused
if (game.isPaused) {
// game loop is not running
}// Remove the canvas from the DOM and clean up
game.destroy(true);
// Full cleanup -- pass noReturn=true if you will NEVER create another Phaser instance
// This allows the framework to release additional internal references
game.destroy(true, true);destroy(removeCanvas, noReturn) is asynchronous -- it flags the game for destruction on the next frame. Listen for Phaser.Core.Events.DESTROY to react to completion.
The Game instance exposes key managers as properties, accessible from any Scene via this.game:
| Property | Type | Description |
|---|---|---|
game.config | Phaser.Core.Config | Parsed GameConfig (read-only after boot) |
game.scene | SceneManager | Start, stop, switch, and manage all scenes |
game.registry | DataManager | Shared data store across all scenes |
game.anims | AnimationManager | Global animation definitions |
game.cache | CacheManager | Stores loaded non-texture assets (JSON, XML, etc.) |
game.textures | TextureManager | Stores all loaded textures and sprite sheets |
game.sound | SoundManager | Global sound playback manager |
// Example: access the registry from any scene
this.game.registry.set('highScore', 9999);
// Example: access the scene manager
this.game.scene.start('MenuScene');scale vs top-level config. width, height, zoom, and parent can be set at the top level or inside scale. The scale sub-object values take priority. Avoid setting both to prevent confusion.
Phaser.WEBGL has no fallback. Unlike AUTO, using Phaser.WEBGL directly will not fall back to Canvas if WebGL is unavailable. The game will fail silently.
parent: null vs parent: undefined. undefined (or omitted) appends the canvas to document.body. null means Phaser will not add the canvas to the DOM at all -- you must do it yourself.
transparent overrides backgroundColor. When transparent: true, the background color is forced to rgba(0,0,0,0) regardless of what you set.
fps.target does not enforce frame rate. It is advisory only. Use fps.limit to actually cap the frame rate. The browser's display refresh rate is always the upper bound.
fps.limit only slows down, never speeds up. Setting limit: 120 on a 60Hz display still results in 60 FPS.
DOM Container requires a parent. Setting dom.createContainer: true without providing a parent element will not work.
smoothPixelArt is WebGL-only. It has no effect with the Canvas renderer.
window.FORCE_WEBGL and window.FORCE_CANVAS. Config.js checks for these globals at the end of parsing and will override the type setting. This is intended for development/testing.
Game.destroy() is asynchronous. It flags the game for destruction on the next frame. Listen for the DESTROY event to react to completion. Pass noReturn: true only if you will never create another Phaser instance on the same page.
1024 (was 800), height to 768 (was 600).Phaser.Scale.EXPAND (value 6) is new -- combines RESIZE visible area behavior with FIT canvas scaling.loader.maxRetries defaults to 2 (was 0 in early v3).render.renderNodes property for custom WebGL render node registration.| Concept | File |
|---|---|
| Game class / boot sequence | src/core/Game.js |
| Config parsing / all defaults | src/core/Config.js |
| GameConfig typedef | src/core/typedefs/GameConfig.js |
| Renderer constants (AUTO, WEBGL, CANVAS, HEADLESS) | src/const.js |
| FPSConfig typedef | src/core/typedefs/FPSConfig.js |
| RenderConfig typedef | src/core/typedefs/RenderConfig.js |
| ScaleConfig typedef | src/core/typedefs/ScaleConfig.js |
| Scale mode constants | src/scale/const/SCALE_MODE_CONST.js |
| Center constants | src/scale/const/CENTER_CONST.js |
| Zoom constants | src/scale/const/ZOOM_CONST.js |
| TimeStep (game loop) | src/core/TimeStep.js |
| Renderer creation | src/core/CreateRenderer.js |
| ScaleManager | src/scale/ScaleManager.js |
| CallbacksConfig typedef | src/core/typedefs/CallbacksConfig.js |
| DOMContainerConfig typedef | src/core/typedefs/DOMContainerConfig.js |
| InputConfig typedef | src/core/typedefs/InputConfig.js |
| LoaderConfig typedef | src/core/typedefs/LoaderConfig.js |
| All core typedefs | src/core/typedefs/ |
© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in store/agents/phaser/skills/game-setup-and-config of autonomous-ai/openharness.
Open the folder on GitHubat commit cc4983e
Game Setup And Config next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Game Setup And Config this skillautonomous-ai/openharness | 1.2k | — | ~4.9k | Automated safety check: Pass | MIT | |
| Game Asset Generatorhtdt/godogen | 7.1k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Asset Pipelinerehan-remade/universal-modder | 6.5k | — | ~2k | Automated safety check: Pass | MIT | |
| Game Asset Generatornotque/vexjoy-agent | 441 | — | ~2.3k | Automated safety check: Notes | MIT | |
| Phaser4 Gamedevchongdashu/vibejam-starter-pack | 149 | — | ~2.8k | Automated safety check: Pass | None | |
| Fal Assetsrehan-remade/universal-modder | 6.5k | — | ~2k | Automated safety check: Notes | MIT |
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
rehan-remade/universal-modder
Turn generated or hand-made art into exactly what a game engine loads.
notque/vexjoy-agent
Deterministic palette/matrix pixel art (not AI). An agent skill from notque/vexjoy-agent.
chongdashu/vibejam-starter-pack
Build 2D browser games with Phaser 4: WebGL-first rendering, scenes, filters, lighting, shaders, DynamicTexture and RenderTexture, tilemaps, SpriteGPULayer, TilemapGPULayer, and Phaser 3 to 4…
rehan-remade/universal-modder
Generate game assets with fal (fal.ai) through the fal MCP server, the um fal CLI (REST) or fal api.
Mojang/minecraft-creator-tools
Design or change how things look in a Minecraft Bedrock Edition add-on - 3D models and textures for mobs, and pixel-art icons for items and textures for blocks.
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Categories
A skill your agent uses when creating a new Phaser 4 game instance or configuring GameConfig options. Game Setup And Config is an agent skill from autonomous-ai/openharness. Use this skill when creating a new Phaser 4 game instance or configuring GameConfig options.
Game Setup And Config fits situations like: creating a new Phaser 4 game instance; configuring GameConfig options; : new Phaser.Game.
Run `npx skills add autonomous-ai/openharness --skill game-setup-and-config -a claude-code`. Or copy the skill folder (store/agents/phaser/skills/game-setup-and-config in autonomous-ai/openharness) into .claude/skills/game-setup-and-config in your project. Claude Code loads it when a task matches its description.
Run `npx skills add autonomous-ai/openharness --skill game-setup-and-config -a codex`. Or copy the skill folder (store/agents/phaser/skills/game-setup-and-config in autonomous-ai/openharness) into .agents/skills/game-setup-and-config in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill game-setup-and-config -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/game-setup-and-config, .gemini/skills/game-setup-and-config, .github/skills/game-setup-and-config and .opencode/skills/game-setup-and-config in your project.
SKILL.md names no scripts, command-line tools or credentials: Game Setup And Config is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: phaser.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Game Setup And Config is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Game Setup And Config: Game Asset Generator (htdt/godogen, 7.1k stars), Asset Pipeline (rehan-remade/universal-modder, 6.5k stars), Game Asset Generator (notque/vexjoy-agent, 441 stars) and Phaser4 Gamedev (chongdashu/vibejam-starter-pack, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.