build-app

build-app is a skill for Claude Code, Codex from playcanvas/create-playcanvas. It costs 46 tokens per session (534 once invoked), scanned A, original, MIT.

A PlayCanvas workflow for creating or restructuring an application using the direct engine API, React, or web components. PlayCanvas is a browser game engine, while React and web components are different ways to build its interface.

In plain words
What is it for?
Use it to inspect a project, select its authoring approach, set up the application, manage lifecycle and assets, configure display density, and verify the real canvas resolution.
Why use it?
It helps preserve the project’s existing lifecycle and choose the right startup, ownership, asset-loading, and engine-connection patterns.

Skill for Claude CodeCodex

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

Good fit Use it to inspect a project, select its authoring approach, set up the application, manage lifecycle and assets, configure display density, and verify the real canvas resolution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/playcanvas/create-playcanvas/build-app
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.

Any agent
npx skills add playcanvas/create-playcanvas --skill build-app
Clone the repo
git clone --depth 1 https://github.com/playcanvas/create-playcanvas

Made for: Claude Code, Codex.

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 build-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/playcanvas/create-playcanvas/build-app/github.svg)](https://agentmods.dev/skills/playcanvas/create-playcanvas/build-app)
Your own site
<a href="https://agentmods.dev/skills/playcanvas/create-playcanvas/build-app"><img src="https://agentmods.dev/badge/skills/playcanvas/create-playcanvas/build-app/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 build-app

Your own site · 80×15
<a href="https://agentmods.dev/skills/playcanvas/create-playcanvas/build-app"><img src="https://agentmods.dev/badge/skills/playcanvas/create-playcanvas/build-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.00534
Opus 5.5 $0.00018 $0.00214
Sonnet 5.5 $0.00009 $0.00107
Haiku 4.5 $0.00005 $0.00053

Measured 23d ago against content hash 2640dfa77d35, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-app 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 23d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • build-app — 100% identical, 0 lines differ
skills/build-app/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build an Engine application

Read package.json and the entry point, keep the surface that owns the lifecycle, and read only its reference: direct Engine, React, or Web Components. Choose from imports and markup, not dependencies.

Bootstrap

  • Input is opt-in. app.keyboard, mouse, touch, gamepads, and elementInput stay null unless passed to new Application(canvas, { ... }); UI buttons need new ElementInput(canvas).
  • The Engine adds no window resize listener; call app.resizeCanvas() from your own handler.
  • graphicsDevice.maxPixelRatio defaults to 1. Raise it, at most to window.devicePixelRatio, only where the target holds its frame budget, call app.resizeCanvas(), and confirm with canvas.width / canvas.clientWidth.
  • Rigid bodies stay inert until Ammo loads through WasmModule. Copy the loader from the physics/falling-shapes example with find-examples.
  • devtools defaults to true, so debugging tools can find the app (inspect-runtime). Set it to false only to hide a production build.

Update loop

  • dt is already clamped by app.maxDeltaTime (0.1 s); tune it instead of clamping by hand. app.timeScale scales it, and 0 pauses scaled time.
  • Keep app state explicit and owned in one place; advance time-dependent logic from dt, and reset through the same setup used at start.

UI

  • Render UI from app state; never keep the source of truth in the DOM or UI elements.
  • Use a DOM or React overlay, or Engine screen and element components adapted from a user-interface example.
  • Hide unused elements with enabled = false; an element at opacity 0 still draws.

Ownership

  • Keep one owner for app creation, assets, entities, update callbacks, and teardown.
  • Prefer the surface's declarative primitives. Put per-entity and per-frame behaviour in an Engine Script.
  • Remove external events and resources in the lifecycle that created them.

Read the full file on GitHub · 45 lines

Files

What ships with it

3 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.

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. 23d ago Changed · +2 lines 2640dfa77d35
  2. 24d ago Changed · -1 lines · -8 tokens per session f36448048968
  3. 26d ago Changed · +2 lines 676e542131d7
  4. 1mo ago First seen · 42 lines · 54 tokens per session scan A 36cb0b469f56

Subscribe to this mod's changes

build-app is a skill published in the GitHub repository playcanvas/create-playcanvas (61 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 534 once invoked, about $0.0002 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 2026-08-30.