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.
npx skills add freshtechbro/claudedesignskills --skill playcanvas-enginegit clone --depth 1 https://github.com/freshtechbro/claudedesignskillsWrote 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.
[](https://agentmods.dev/skills/freshtechbro/claudedesignskills/playcanvas-engine)<a href="https://agentmods.dev/skills/freshtechbro/claudedesignskills/playcanvas-engine"><img src="https://agentmods.dev/badge/skills/freshtechbro/claudedesignskills/playcanvas-engine/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.
<a href="https://agentmods.dev/skills/freshtechbro/claudedesignskills/playcanvas-engine"><img src="https://agentmods.dev/badge/skills/freshtechbro/claudedesignskills/playcanvas-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00093 | $0.05859 |
| Opus 5 | $0.00046 | $0.02929 |
| Sonnet 5 | $0.00019 | $0.01172 |
| Haiku 4.5 | $0.00009 | $0.00586 |
Grade A, and why
playcanvas-engine 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- playcanvas-engine — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,063 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlayCanvas Engine Skill
Lightweight WebGL/WebGPU game engine with entity-component architecture, visual editor integration, and performance-focused design.
When to Use This Skill
Trigger this skill when you see:
- "PlayCanvas engine"
- "WebGL game engine"
- "entity component system"
- "PlayCanvas application"
- "3D browser games"
- "online 3D editor"
- "lightweight 3D engine"
- Need for editor-first workflow
Compare with:
- Three.js: Lower-level, more flexible but requires more setup
- Babylon.js: Feature-rich but heavier, has editor but less mature
- A-Frame: VR-focused, declarative HTML approach
- Use PlayCanvas for: Game projects, editor-first workflow, performance-critical apps
Core Concepts
1. Application
The root PlayCanvas application manages the rendering loop.
import * as pc from 'playcanvas';
// Create canvas
const canvas = document.createElement('canvas');
document.body.appendChild(canvas);
// Create application
const app = new pc.Application(canvas, {
keyboard: new pc.Keyboard(window),
mouse: new pc.Mouse(canvas),
touch: new pc.TouchDevice(canvas),
gamepads: new pc.GamePads()
});
// Configure canvas
app.setCanvasFillMode(pc.FILLMODE_FILL_WINDOW);
app.setCanvasResolution(pc.RESOLUTION_AUTO);
// Handle resize
window.addEventListener('resize', () => app.resizeCanvas());
// Start the application
app.start();
2. Entity-Component System
PlayCanvas uses ECS architecture: Entities contain Components.
// Create entity
const entity = new pc.Entity('myEntity');
// Add to scene hierarchy
app.root.addChild(entity);
// Add components
entity.addComponent('model', {
type: 'box'
});
entity.addComponent('script');
// Transform
entity.setPosition(0, 1, 0);
entity.setEulerAngles(0, 45, 0);
entity.setLocalScale(2, 2, 2);
// Parent-child hierarchy
const parent = new pc.Entity('parent');
const child = new pc.Entity('child');
parent.addChild(child);
3. Update Loop
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/examples/README.md 20 KB
- assets/starter_playcanvas/index.html 2.0 KB
- assets/starter_playcanvas/README.md 9.2 KB
- assets/starter_playcanvas/scripts/app.js 6.4 KB runs code
- assets/starter_playcanvas/scripts/camera-controller.js 8.3 KB runs code
- assets/starter_playcanvas/scripts/input-manager.js 5.7 KB runs code
- assets/starter_playcanvas/styles.css 4.2 KB
- references/api_reference.md 20 KB
- references/editor_workflow.md 17 KB
- references/optimization_guide.md 18 KB
- scripts/component_builder.py 28 KB runs code
- scripts/project_generator.py 22 KB runs code
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.
- 10d ago First seen · 1,063 lines · 93 tokens per session scan A 5b4abe83ccc3
playcanvas-engine is a skill published in the GitHub repository freshtechbro/claudedesignskills (873 stars, last pushed 9mo ago), licensed MIT. It adds 93 tokens to every session and 5,859 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
react-three-fiber
React Three Fiber 3D renderer for json-render. Use when working with @json-render/react-three-fiber, building 3D scenes from JSON specs, rendering meshes/lights/models/environments, or integrating Three.js with json-render catalogs.
matterjs
Use when implementing 2D physics interactions with Matter.js, including Engine/World setup, Render/Runner configuration, adding bodies and constraints, and scroll/interaction-friendly canvas scenes.
vgpu
Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, and performance work.
threejs-game-director
Entrypoint for building, upgrading, and finishing Three.js browser games. Routes work across the sibling threejs- skills for gameplay, graphics, UI, 3D/image/audio asset generation, debugging, and release. Use for build-a-game, upgrade, polish, premium, AAA, high-fidelity, showcase, from-scratch, endless runner…
build-game-map-editor
Build, extend, or audit production-linked browser map editors for Three.js and isometric games. Use when Codex needs to create a private director view, derive a versioned editor document from authored placements, add outliner, layer, selection, drag, snap, inspector, or camera controls, expose enemy aggro, leash, or…