Agent skill

V4 New Features

by autonomous-ai in autonomous-ai/openharness

A skill your agent uses when learning about new features, game objects, components, and rendering capabilities added in Phaser 4.

MITAuto-check passedGame Development

Install V4 New Features

skills CLI
$ npx skills add autonomous-ai/openharness --skill v4-new-features -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/openharness v4-new-features --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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/v4-new-features .claude/skills/v4-new-features && rm -rf skills-src

Use ~/.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/

Facts

Skill name
v4-new-features
GitHub stars
1.2k
Token cost
~3.8k tokens
SKILL.md length
1,033 words
Files
2 (incl. references)
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when learning about new features, game objects, components, and rendering capabilities added in Phaser 4.

  • Learning about new features
  • SKILL.md covers Overview: What Changed in v4, Filters System (Replacing FX…, RenderNodes (Replacing… and New Game Objects, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Rendering capabilities added in Phaser 4

What it does

V4 New Features is an agent skill from autonomous-ai/openharness. Use this skill when learning about new features, game objects, components, and rendering capabilities added in Phaser 4. Covers Filters, RenderNodes, CaptureFrame, Gradient, Noise, SpriteGPULayer, TilemapGPULayer, Lighting component, RenderSteps, and new tint modes. Triggers on: new in v4, Phaser 4 features, RenderNode, SpriteGPULayer, CaptureFrame, Gradient game object, Noise game object, new tint modes. For migrating v3 code to v4, see the v3-to-v4-migration skill instead.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/REFERENCE.md`).

It sits in Game Development. 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.

When your agent uses it

  • Learning about new features
  • Rendering capabilities added in Phaser 4
  • Phaser 4 features
  • Gradient game object

Example prompts

  • “/v4-new-features”

What it can do on your machine

Read from SKILL.md and the folder at commit cc4983e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

V4 New Features loads about 3.8k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 1,033 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~124
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.5k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 1,033 words, ~3,756 tokens.

Download SKILL.mdSave it as .claude/skills/v4-new-features/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
v4-new-features
description
Use this skill when learning about new features, game objects, components, and rendering capabilities added in Phaser 4. Covers Filters, RenderNodes, CaptureFrame, Gradient, Noise, SpriteGPULayer, TilemapGPULayer, Lighting component, RenderSteps, and new tint modes. Triggers on: new in v4, Phaser 4 features, RenderNode, SpriteGPULayer, CaptureFrame, Gradient game object, Noise game object, new tint modes. For migrating v3 code to v4, see the v3-to-v4-migration skill instead.

Phaser 4 New Features

New features and capabilities in Phaser 4: Filters (replacing FX/BitmapMask), RenderNodes (replacing Pipelines), CaptureFrame, Gradient, Noise game objects, SpriteGPULayer, TilemapGPULayer, Lighting component, RenderSteps, and new tint modes.

Related skills: ../v3-to-v4-migration/SKILL.md, ../filters-and-postfx/SKILL.md, ../game-object-components/SKILL.md, ../tilemaps/SKILL.md

Migrating from v3? See the v3 to v4 Migration Guide for step-by-step code changes, removed APIs, and a migration checklist.

Overview: What Changed in v4

Phaser 4 is a complete overhaul of the WebGL rendering engine. The v3 renderer let each subsystem manage WebGL state independently, causing conflicts (e.g. certain FX breaking Masks). v4 centralizes WebGL state management through a RenderNode graph, where each node handles exactly one rendering task.

Key Removals
v3 Featurev4 Replacement
PipelineRenderNode (per-task rendering nodes)
FX (preFX / postFX)Filters (filters.internal / filters.external)
BitmapMaskFilterMask (via filters system)
GeometryMask (WebGL)FilterMask (Canvas still uses GeometryMask)
Derived FX: Bloom, Circle, Gradient, ShineActions (AddEffectBloom, AddEffectShine, AddMaskShape) or GameObjects
Mesh and PlaneRemoved (proper 3D planned for future)
PointUse Vector2 instead
Key Additions
  • New GameObjects: CaptureFrame, Gradient, Noise, NoiseCell2D/3D/4D, NoiseSimplex2D/3D, SpriteGPULayer, Stamp, TilemapGPULayer
  • New Components: Lighting, RenderSteps, RenderNodes
  • New Tint Modes: MULTIPLY, FILL, ADD, SCREEN, OVERLAY, HARD_LIGHT
  • New Filters: Blend, Blocky, CombineColorMatrix, GradientMap, ImageLight, Key, Mask, NormalTools, PanoramaBlur, ParallelFilters, Quantize, Sampler, Threshold
  • GL Orientation: v4 uses standard GL orientation (Y=0 at bottom for textures)

Filters System (Replacing FX and BitmapMask)

Full reference: filters-and-postfx.md

Filters unify the v3 FX and Mask systems. Every filter takes an input image and produces an output image via a shader pass. Filters can be applied to any game object or camera -- v3 had restrictions on which objects supported FX.

js
// v3 approach (FX):
sprite.preFX.addGlow(0xff00ff, 4);
sprite.postFX.addBlur(0, 2, 2, 1);

// v4 approach (Filters):
sprite.enableFilters();
sprite.filters.internal.addGlow(0xff00ff, 4, 0, 1);
sprite.filters.external.addBlur(0, 2, 2, 1);

// v3 approach (BitmapMask):
const mask = new Phaser.Display.Masks.BitmapMask(scene, maskImage);
sprite.setMask(mask);

// v4 approach (FilterMask):
sprite.enableFilters();
sprite.filters.internal.addMask(maskImage);

Internal vs External: Internal filters run before the camera transform (object-local space, cheaper). External filters run after (screen space, full-resolution).


RenderNodes (Replacing Pipelines)

In v3, a Pipeline was a rendering system that often handled multiple responsibilities. In v4, each RenderNode handles a single rendering task via its run() method. Some nodes also have a batch() method to accumulate state before drawing.

Architecture

The RenderNodeManager (on the WebGL renderer) owns all render nodes. Game objects reference nodes through role-based maps.

js
// RenderNode roles on a game object:
// - 'Submitter': runs other node roles for each element
// - 'Transformer': provides vertex coordinates
// - 'Texturer': handles textures

// GameObjects have default and custom render node maps:
gameObject.defaultRenderNodes  // built-in nodes per role
gameObject.customRenderNodes   // overrides per role
gameObject.renderNodeData      // data keyed by node name
Setting Custom RenderNodes
js
// Override a specific render role:
gameObject.setRenderNodeRole('Submitter', 'MyCustomSubmitter');

// Pass data to a render node:
gameObject.setRenderNodeRole('Transformer', 'MyTransformer', {
    customProperty: 42
});

// Remove a custom node (falls back to default):
gameObject.setRenderNodeRole('Submitter', null);
Built-in RenderNode Types

Batch Handlers (accumulate and draw multiple objects per draw call):

  • BatchHandlerQuad -- standard quad batching (Image, Sprite, BitmapText, etc.)
  • BatchHandlerQuadSingle -- single-quad variant
  • BatchHandlerTileSprite -- TileSprite batching
  • BatchHandlerTriFlat -- flat triangle batching (Graphics, Shape)
  • BatchHandlerPointLight -- point light batching
  • BatchHandlerStrip -- triangle strip batching

Submitters (coordinate rendering per object type):

  • SubmitterQuad, SubmitterTile, SubmitterTileSprite
  • SubmitterSpriteGPULayer, SubmitterTilemapGPULayer

Transformers (compute vertex positions):

  • TransformerImage, TransformerStamp, TransformerTile, TransformerTileSprite

Texturers (manage texture binding):

  • TexturerImage, TexturerTileSprite

Filters (post-processing -- see filters-and-postfx.md):

  • BaseFilter, BaseFilterShader
  • FilterBarrel, FilterBlend, FilterBlocky, FilterBlur (Low/Med/High variants)
  • FilterBokeh, FilterColorMatrix, FilterCombineColorMatrix
  • FilterDisplacement, FilterGlow, FilterGradientMap, FilterImageLight
  • FilterKey, FilterMask, FilterNormalTools, FilterPanoramaBlur
  • FilterParallelFilters, FilterPixelate, FilterQuantize
  • FilterSampler, FilterShadow, FilterThreshold, FilterVignette, FilterWipe

Other:

  • Camera, FillCamera, FillRect, FillPath, FillTri
  • DrawLine, StrokePath, ShaderQuad
  • ListCompositor, RebindContext, YieldContext
  • DynamicTextureHandler
Extending: Custom RenderNodes
js
// Register a custom node constructor:
renderer.renderNodes.addNodeConstructor('MyNode', MyNodeClass);

// Or add a pre-built node instance:
renderer.renderNodes.addNode('MyNode', myNodeInstance);

New Game Objects

CaptureFrame

Captures the current framebuffer contents to a texture at the point in the display list where it sits. Does not render anything itself. WebGL only.

js
// Everything above this in the display list gets captured:
const image1 = this.add.image(400, 300, 'background');

// Enable framebuffer usage on the camera:
this.cameras.main.setForceComposite(true);

// Create the capture point:
const capture = this.add.captureFrame('myCapturedTexture');

// Use the captured texture on another object:
const overlay = this.add.image(400, 300, 'myCapturedTexture');
// Add filters to the overlay to distort the captured scene

Key details:

  • Requires camera.setForceComposite(true) or a framebuffer context (Filters, DynamicTexture, camera with partial alpha)
  • Inside a Container with filters, captures only that Container's contents
  • Setting visible = false stops capturing
  • Components: BlendMode, Depth, RenderNodes, Visible

Source: src/gameobjects/captureframe/CaptureFrame.js

Gradient

Displays GPU-rendered color gradients. Extends Shader. Supports linear, radial, and other shape modes with configurable ColorRamp containing ColorBand objects.

js
// Simple linear gradient:
const grad = this.add.gradient(undefined, 100, 100, 200, 200);

// Complex radial gradient with multiple color bands:
const halo = this.add.gradient({
    bands: [
        { start: 0.5, end: 0.6, colorStart: [0.5, 0.5, 1, 0], colorEnd: 0xffffff, colorSpace: 1, interpolation: 4 },
        { start: 0.6, end: 1, colorStart: 0xffffff, colorEnd: [1, 0.5, 0.5, 0], colorSpace: 1, interpolation: 3 }
    ],
    dither: true,
    repeatMode: 1,
    shapeMode: 2,       // radial
    start: { x: 0.5, y: 0.5 },
    shape: { x: 0.5, y: 0.0 }
}, 400, 300, 800, 800);

// Animate:
halo.offset = 0.1 * (1 + Math.sin(time / 1000));

Key details:

  • Config: GradientQuadConfig with bands, shapeMode, repeatMode, start, shape, dither
  • Colors defined via ColorRamp with ColorBand objects (supports HSV, various interpolation modes)
  • Call gradient.ramp.encode() after modifying ramp data at runtime

Source: src/gameobjects/gradient/Gradient.js

Show full SKILL.md (456 more words)Show less
Noise Game Objects

All noise types extend Shader and are WebGL only. Six variants available:

TypeFactoryDescription
Noisethis.add.noise()White noise (random hash-based)
NoiseCell2Dthis.add.noiseCell2D()2D cellular/Worley/Voronoi noise
NoiseCell3Dthis.add.noiseCell3D()3D cellular noise (Z-axis slicing for animation)
NoiseCell4Dthis.add.noiseCell4D()4D cellular noise (Z+W axis slicing)
NoiseSimplex2Dthis.add.noiseSimplex2D()2D simplex/gradient noise (clouds, fire, water)
NoiseSimplex3Dthis.add.noiseSimplex3D()3D simplex noise
js
// Basic white noise:
const noise = this.add.noise({
    noiseOffset: [0, 0],
    noisePower: 1
}, 100, 100, 256, 256);

// Cellular noise with customization:
const cells = this.add.noiseCell2D({
    noiseOffset: [0, 0],
    noiseIterations: 3,
    noiseNormalMap: true    // output as normal map for lighting
}, 200, 200, 256, 256);

// Simplex noise for natural effects:
const simplex = this.add.noiseSimplex2D({
    noiseFlow: 0,           // animate this for evolution
    noiseIterations: 4,
    noiseWarpAmount: 0.5,   // turbulence
    noiseSeed: 42,
    noiseNormalMap: false
}, 300, 300, 256, 256);

Common properties across noise types:

  • noiseOffset -- [x, y] array to scroll the pattern
  • noisePower -- sculpt output levels (higher suppresses high values)
  • noiseNormalMap -- output normal map (for lighting integration)
  • noiseIterations -- detail level (cellular/simplex types)

Math equivalents: Phaser.Math.Hash(), Phaser.Math.HashCell(), Phaser.Math.HashSimplex()

Source: src/gameobjects/noise/

SpriteGPULayer

Renders very large numbers of quads (up to millions) in a single draw call by storing data in a static GPU buffer. Up to 100x faster than individual sprites. WebGL only.

js
const layer = this.add.spriteGPULayer(texture, size); // size = max number of members

// Add members (do this all at once, not incrementally):
const member = { x: 100, y: 200, frame: 'tree', scaleX: 1, scaleY: 1, alpha: 1 };
layer.addMember(member);

// Reuse the member object for efficiency with millions of entries:
member.x = 300;
member.y = 400;
member.frame = 'bush';
layer.addMember(member);

// Enable lighting on the layer:
layer.setLighting(true);

Key details:

  • Single texture only (no multi-atlas), single image per layer
  • Members support tween-like animations (fade, bounce, wave, color shift) defined at creation
  • Updating buffer contents is expensive -- populate once, leave unchanged
  • Power-of-two textures recommended for pixel art to avoid seaming
  • "Remove" members visually by setting scaleX/scaleY/alpha to 0 (avoids buffer rebuild)
  • Components: Alpha, BlendMode, Depth, ElapseTimer, Lighting, Mask, RenderNodes, TextureCrop, Visible

Source: src/gameobjects/spritegpulayer/SpriteGPULayer.js


New Components

Full component reference: game-object-components.md

Lighting Component

Replaces the v3 approach of assigning a lighting pipeline. WebGL only.

js
// v3 approach:
sprite.setPipeline('Light2D');

// v4 approach:
sprite.setLighting(true);

// Self-shadowing (simulates surface shadows from texture brightness):
sprite.setSelfShadow(true, 0.5, 1/3);
// Args: enabled, penumbra (lower = sharper), diffuseFlatThreshold (0-1)

// Use game-wide default for self-shadow:
sprite.setSelfShadow(null);  // reads from config.render.selfShadow

Supported on: BitmapText, Blitter, Graphics, Shape, Image, Sprite, Particles, SpriteGPULayer, Stamp, Text, TileSprite, Video, TilemapLayer, TilemapGPULayer.

Batching note: Lighting changes the shader, which breaks batches. Group lit objects together and unlit objects together for best performance.

Source: src/gameobjects/components/Lighting.js

RenderSteps Component

Allows injecting custom logic into the render process of a game object. WebGL only. The Filters system uses RenderSteps internally.

js
// Add a custom render step:
gameObject.addRenderStep(function (renderer, gameObject, drawingContext, parentMatrix, renderStep, displayList, displayListIndex) {
    // Custom rendering logic here
    // Call next step when ready:
    var nextFn = gameObject._renderSteps[renderStep + 1];
    if (nextFn) {
        nextFn(renderer, gameObject, drawingContext, parentMatrix, renderStep + 1, displayList, displayListIndex);
    }
});

Key details:

  • Steps are stored in _renderSteps array, executed via renderWebGLStep()
  • First step runs first and is responsible for calling subsequent steps
  • This is how Filters defer and control the renderWebGL flow

Source: src/gameobjects/components/RenderSteps.js

RenderNodes Component

Provides defaultRenderNodes, customRenderNodes, and renderNodeData maps on game objects. See the RenderNodes section above for usage.

Source: src/gameobjects/components/RenderNodes.js


TilemapGPULayer

Full tilemap reference: tilemaps.md

High-performance GPU-based tilemap rendering. Renders the entire layer as a single quad via a specialized shader. WebGL only.

js
// Create via Tilemap with the gpu flag:
const map = this.make.tilemap({ key: 'level1' });
const tileset = map.addTilesetImage('tiles', 'tilesImage');
const gpuLayer = map.createLayer('Ground', tileset, 0, 0, true);  // last arg: gpu = true

Capabilities:

  • Single tileset with single texture image
  • Maximum 4096x4096 tiles, up to 2^23 unique tile IDs
  • Tile flipping and animation supported
  • Orthographic tilemaps only (no isometric/hexagonal)
  • Perfect texture filtering in LINEAR mode (no tile seams)
  • Cost is per-pixel, not per-tile -- no performance loss with many visible tiles

Restrictions:

  • Cannot use multiple tilesets
  • Editing requires manual generateLayerDataTexture() call to update
  • Orthographic only

Internal data: Tile data stored in a texture (4 bytes/tile: 2 flip bits, 1 animation bit, 1 unused, 28-bit tile index). Animation data in a separate texture.

Source: src/tilemaps/TilemapGPULayer.js


For detailed configuration options, API reference tables, and source file maps, see the reference guide.

© 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

Files

SKILL.md and 1 other file (references) in store/agents/phaser/skills/v4-new-features of autonomous-ai/openharness.

  • SKILL.md
  • references/REFERENCE.md

Open the folder on GitHubat commit cc4983e

Compare with similar skills

V4 New Features 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.

V4 New Features compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
V4 New Features this skillautonomous-ai/openharness1.2k—~3.8kAutomated safety check: PassMIT
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
Web CloneJane-xiaoer/claude-skill-web-clone1k1 repos~2.7kAutomated safety check: PassMIT
Threejs Game Directormajidmanzarpour/threejs-game-skills2.5k—~2.2kAutomated safety check: PassMIT
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed
  • Web Clone

    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…

    1k GitHub starsUsed in 1 repo~2.7k tokens
    Game DevelopmentAuto-check passed
  • Threejs Game Director

    majidmanzarpour/threejs-game-skills

    Entrypoint for building, upgrading, and finishing Three.js browser games.

    2.5k GitHub stars~2.2k tokensUpdated 12 days ago
    Game DevelopmentAuto-check passed
  • Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 9 days ago
    Game DevelopmentAuto-check passed
  • Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed
  • Uloop Execute Dynamic Code

    CyberAgentGameEntertainment/NovaShader

    Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.

    1.6k GitHub starsUsed in 1 repo~1.9k tokens
    Game DevelopmentAuto-check passed

More from autonomous-ai/openharness

All 100 skills in this repo
  • G-code Slicer Tool

    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.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Home Assistant Automation Builder

    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.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • OrcaSlicer 3MF and G-code Workflow

    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.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Sheets and Docs Report Builder

    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.

    1.2k GitHub stars~708 tokensUpdated today
    Auto-check passed
  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.2k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about V4 New Features

What does V4 New Features do?

A skill your agent uses when learning about new features, game objects, components, and rendering capabilities added in Phaser 4. V4 New Features is an agent skill from autonomous-ai/openharness. Use this skill when learning about new features, game objects, components, and rendering capabilities added in Phaser 4.

When should I use V4 New Features?

V4 New Features fits situations like: learning about new features; rendering capabilities added in Phaser 4; phaser 4 features; gradient game object.

How do I install V4 New Features in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill v4-new-features -a claude-code`. Or copy the skill folder (store/agents/phaser/skills/v4-new-features in autonomous-ai/openharness) into .claude/skills/v4-new-features in your project. Claude Code loads it when a task matches its description.

How do I install V4 New Features in Codex?

Run `npx skills add autonomous-ai/openharness --skill v4-new-features -a codex`. Or copy the skill folder (store/agents/phaser/skills/v4-new-features in autonomous-ai/openharness) into .agents/skills/v4-new-features in your project. Codex loads it when a task matches its description.

Can I use V4 New Features in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill v4-new-features -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/v4-new-features, .gemini/skills/v4-new-features, .github/skills/v4-new-features and .opencode/skills/v4-new-features in your project.

What does V4 New Features need to run?

SKILL.md names no scripts, command-line tools or credentials: V4 New Features is instructions for the agent only.

Does V4 New Features access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is V4 New Features safe to install?

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.

What licence does V4 New Features use?

V4 New Features is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does V4 New Features use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 745 tokens, read only when the agent opens those files.

What are the alternatives to V4 New Features?

Skills that share tags, products or a category with V4 New Features: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains V4 New Features?

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.