threejs-ai-skill

threejs-ai-skill is a skill for Claude Code, Codex from luisnavarrete12/threejs-ai-skill. It costs 213 tokens per session (1,416 once invoked), scanned A, original, MIT.

A guide for generating Three.js, WebGL, or React Three Fiber 3D scenes that behave like coherent physical spaces. It covers scale, placement, camera setup, collisions, controls, and character movement.

In plain words
What is it for?
Use it when building playable 3D scenes, setting up worlds and cameras, adding collision handling and controls, or making characters move and animate correctly.
Why use it?
It addresses common problems in generated 3D code, such as floating or overlapping objects, incorrect model orientation, missing collisions, and inconsistent movement.

Skill for Claude CodeCodex

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

Good fit Use it when building playable 3D scenes, setting up worlds and cameras, adding collision handling and controls, or making characters move and animate correctly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill
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 luisnavarrete12/threejs-ai-skill --skill threejs-ai-skill
Clone the repo
git clone --depth 1 https://github.com/luisnavarrete12/threejs-ai-skill

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-ai-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill/github.svg)](https://agentmods.dev/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill)
Your own site
<a href="https://agentmods.dev/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill"><img src="https://agentmods.dev/badge/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill/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-ai-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill"><img src="https://agentmods.dev/badge/skills/luisnavarrete12/threejs-ai-skill/threejs-ai-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 213 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,416 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 $0.00213 $0.01416
Opus 5 $0.00106 $0.00708
Sonnet 5 $0.00043 $0.00283
Haiku 4.5 $0.00021 $0.00142

Measured 10d ago against content hash 2c7b4a8e7694, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

threejs-ai-skill 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.

SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Three.js AI Skill

AI-generated Three.js code almost always compiles — and then looks and feels broken. Models load at the wrong scale facing random directions; objects spawn at arbitrary coordinates, float, or clip through everything; the camera drifts unframed; there are never any collisions; controls are frame-rate-dependent and don't handle diagonals; and characters slide across the floor while their legs move out of sync.

The root cause is always the same: the model writes code without reasoning about the physical and spatial rules of a real 3D world. This skill encodes those rules as layers. Read the layer(s) relevant to the request; each builds on the one before.

The layer stack

  1. Scene sanity (this file, §1) — scale, orientation, lighting, camera, placement, renderer setup. Every scene needs this.
  2. World coherencereferences/world-coherence.md — no infinite spawns, relative scale, everything on the ground, framed camera, intentional layout.
  3. Collisionsreferences/collision-bounds.md — objects that don't pass through everything; test-before-move; when to use a physics engine.
  4. Input & controlsreferences/input-controls.md — deltaTime, normalized diagonals, multi-key, clamped mouse-look.
  5. Locomotionreferences/locomotion.md — characters that walk without sliding or floating; turn toward movement; blend idle/walk/run. (Verify visually — hard to get right.)
  6. Animation handlingreferences/animation-handling.md — play clips, retarget animation from another file, and procedural motion for models with no animation. (Procedural is experimental — always test the visual result before trusting it.)

Read references/model-normalization.md for the drop-in model-loading helpers referenced throughout.

react-three-fiber: every rule below applies unchanged — r3f is a renderer binding, not a different engine. Prefer drei equivalents where they exist (<Bounds> for framing, <Environment> for IBL, <OrbitControls makeDefault>), and do movement/physics work in useFrame((_, delta) => ...), never in useEffect or render.

Read the full file on GitHub · 68 lines

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. 10d ago First seen · 68 lines · 213 tokens per session scan A 2c7b4a8e7694

Subscribe to this mod's changes

threejs-ai-skill is a skill published in the GitHub repository luisnavarrete12/threejs-ai-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 1,416 once invoked, about $0.0011 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 2026-08-31.

Related

Other skills, from other repositories

THREE.Terrain

Use this guide when an agent must build, modify, inspect, or document a terrain scene with THREE.Terrain. The library creates heightmapped Three.js terrain and provides procedural generators, filters, material blending, decoration tools, grass, image conversion, analysis, and seeded randomness.

IceCreamYou/THREE.Terrain · 0 tokens

muapi-storyboard

Generate N keyframes for a short story or scene sequence (image only, no video).

SamurAIGPT/Generative-Media-Skills · 23 tokens

game-opportunity

A research workflow for finding promising opportunities to build small game websites. It checks new game names, search demand, competition, recent trends, and whether a playable game exists.

yan-labs/yan-skills · 91 tokens

reversing-unity-il2cpp

Reverse engineer Unity games and apps built with IL2CPP or Mono, using Il2CppDumper, Il2CppInspector, and dnSpy. Use when an APK or IPA contains global-metadata.dat, libil2cpp.so, UnityFramework, or Assembly-CSharp.dll, when jadx shows only UnityPlayerActivity, or when the target is described as a Unity build.

trilwu/secskills · 85 tokens

hz-unity-meta-mixed-reality-utility-kit

Meta XR Mixed Reality Utility Kit (MRUK) (com.meta.xr.mrutilitykit) for Unity XR development. Use when working with Scene API data (rooms, walls, floors, furniture), spawning prefabs on scene anchors, placing virtual objects in the real world, world locking to prevent anchor drift, raycasting against room geometry…

meta-quest/agentic-tools · 136 tokens

hz-unity-meta-movement-sdk-retargeting

Set up and tweak Meta Movement SDK (MSDK) retargeting for a character model. Use this whenever the user wants to retarget a humanoid FBX/prefab for Meta Quest body tracking, generate a retargeting config, or hand-edit the resulting .json (fix known-joint mappings, exclude joints from auto-mapping, rename target…

meta-quest/agentic-tools · 182 tokens