threejs-agents-scene-builder

threejs-agents-scene-builder is a skill for Claude Code, Codex from Impertio-Studio/Three.js-Claude-Skill-Package. It costs 102 tokens per session (3,272 once invoked), scanned A, original, MIT.

A planning guide for building complete 3D scenes with Three.js, a JavaScript library for 3D graphics. It helps choose cameras, lighting, materials, controls, rendering style, and effects for different types of scenes.

In plain words
What is it for?
Use it when creating a Three.js visualization or scene from scratch, including choosing React Three Fiber for React projects or regular Three.js for other setups.
Why use it?
Starting a 3D scene involves many connected choices, and the right setup depends on whether you are making a product viewer, walkthrough, game, chart, or other experience.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it when creating a Three.js visualization or scene from scratch, including choosing React Three Fiber for React projects or regular Three.js for other setups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder
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 Impertio-Studio/Three.js-Claude-Skill-Package --skill threejs-agents-scene-builder
Clone the repo
git clone --depth 1 https://github.com/Impertio-Studio/Three.js-Claude-Skill-Package

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 threejs-agents-scene-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder/github.svg)](https://agentmods.dev/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder)
Your own site
<a href="https://agentmods.dev/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder"><img src="https://agentmods.dev/badge/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder/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 threejs-agents-scene-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder"><img src="https://agentmods.dev/badge/skills/impertio-studio/three.js-claude-skill-package/threejs-agents-scene-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,272 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 $0.00102 $0.03272
Opus 5 $0.00051 $0.01636
Sonnet 5 $0.00020 $0.00654
Haiku 4.5 $0.00010 $0.00327

Measured 9d ago against content hash 73e2b175f59b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

threejs-agents-scene-builder 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 9d 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/source/threejs-agents/threejs-agents-scene-builder/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

threejs-agents-scene-builder

Purpose

This skill is an orchestration guide for building complete Three.js scenes. It provides decision trees that map use cases to the correct combination of lighting, materials, camera, controls, environment, and post-processing. ALWAYS consult this skill first when asked to create a 3D scene or visualization.


Master Decision Tree: Use Case to Scene Recipe

Step 1: Identify the Use Case

Use Case Go To
Product viewer / configurator Recipe A
Architectural walkthrough Recipe B
Game level / interactive 3D Recipe C
Data visualization / chart Recipe D
Portfolio / hero section Recipe E
CAD / BIM / IFC viewer Recipe F
AR / XR experience Recipe G

Step 2: Choose R3F vs Imperative

Condition Decision
Project uses React ALWAYS use React Three Fiber (R3F)
Project uses Vue, Svelte, or vanilla JS ALWAYS use imperative Three.js
Need maximum control over render loop Prefer imperative Three.js
Rapid prototyping with component reuse Prefer R3F + Drei
Static scene, no interaction framework Either works; imperative is lighter

Cross-reference: threejs-impl-r3f for R3F patterns, threejs-core-scene-graph for imperative patterns.


Decision Tree: Lighting Setup

Step 1: Scene Type to Lighting Strategy

Scene Type Primary Light Fill Light Shadows
Outdoor / daylight DirectionalLight (sun) HemisphereLight (sky/ground) DirectionalLight shadow, PCFSoftShadowMap
Indoor / room PointLight or SpotLight (fixtures) AmbientLight (low) SpotLight shadows, limit to 2-3
Studio / product SpotLight (key) + SpotLight (rim) AmbientLight or HemisphereLight ContactShadows (Drei) or AccumulativeShadows
Stylized / toon DirectionalLight HemisphereLight Optional; BasicShadowMap for hard edges
HDR environment only None (IBL provides all lighting) None ContactShadows or AccumulativeShadows
Night / dark SpotLight (focused pools) AmbientLight (very low, ~0.05) SpotLight shadows

Read the full file on GitHub · 296 lines

Files

What ships with it

4 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. 9d ago First seen · 296 lines · 102 tokens per session scan A 73e2b175f59b

Subscribe to this mod's changes

threejs-agents-scene-builder is a skill published in the GitHub repository Impertio-Studio/Three.js-Claude-Skill-Package (13 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 3,272 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.