image-to-threejs

image-to-threejs is a skill for Claude Code from kyh/vibedgames. It costs 186 tokens per session (5,926 once invoked), scanned A, original, MIT.

A workflow for rebuilding an object from a reference image as procedural Three.js code, using simple shapes, materials, and named attachment points instead of a saved 3D model file.

In plain words
What is it for?
Use it to create game props such as hinged, opening, detachable, or breakable objects in Three.js. It requires uv, Python 3.12, and a one-time repository clone.
Why use it?
It provides a code-based asset that can be resized, recolored, varied, and animated by changing the source code. It is intended for objects with parts that move, detach, or break.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the asset-pipeline plugin — 5 skills shipped together

Good fit Use it to create game props such as hinged, opening, detachable, or breakable objects in Three.js. It requires uv, Python 3.12, and a one-time repository clone.

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

Made for: Claude Code.

Or install asset-pipeline, the plugin that ships this one along with the rest of its 5 skills.

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 image-to-threejs

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kyh/vibedgames/image-to-threejs"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/image-to-threejs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,926 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 65
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00186 $0.05926
Opus 5 $0.00093 $0.02963
Sonnet 5 $0.00037 $0.01185
Haiku 4.5 $0.00019 $0.00593

Measured 6d ago against content hash b82c12b85544, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

image-to-threejs 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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_lib/asset-tools.mjs, scripts/align_framing.py, scripts/normalize-factory.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/asset-pipeline/skills/image-to-threejs/SKILL.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image to Three.js

Prerequisites — read before starting. This skill is not Node-only. Its generator is an external Python program, so it needs uv and Python 3.12 on the machine plus a one-time git clone (see Setup). Every other asset-pipeline skill runs on node alone; this one does not. If uv is not available and cannot be installed, stop here and pick a different approach rather than starting the pipeline — the wall arrives several steps in.

Rebuild an object as procedural Three.js code driven by one generated reference image. The output is a TypeScript factory — primitives, procedural materials, and a named pivot/socket rig — not a .glb.

This is the 3D sibling of animated-spritesheets: generate one clean image with vg generate, run it through a staged pipeline, get a game-ready asset.

Pick this or a mesh — they are not interchangeable

Need Use
Prop that hinges, opens, detaches, or breaks this skill — the rig is the point
Prop you want to tweak in code (size, palette, variants) this skill — it's source
Organic/photoreal shape, character, anything sculpted vg generate → Meshy (model-catalog, regenerate-3d)
Generic set dressing, many objects, ship today Kenney kit GLBs — free and instant
Whole scenes, crowds, LOD-heavy fills not this — see the token budget below

Budget before you start. Upstream measures ~80k–180k tokens per object and 150k–350k per character, dominated by 5–8 render-review cycles. This is for a handful of hero props, never for populating a scene. The cheapest lever is a good reference image — one avoided bad render saves 10k–20k tokens.

Read the full file on GitHub · 428 lines

Files

What ships with it

5 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. 6d ago Changed · +102 lines b82c12b85544
  2. 10d ago First seen · 326 lines · 186 tokens per session scan A 43057f2a0bd1

Subscribe to this mod's changes

image-to-threejs is a skill published in the GitHub repository kyh/vibedgames (55 stars, last pushed today), licensed MIT. It adds 186 tokens to every session and 5,926 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

migrate-radix-to-base

Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.

shadcn-ui/ui · 61 tokens

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.

react/react · 42 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens

a2ui-renderer

Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…

CopilotKit/CopilotKit · 175 tokens

copilotkit-develop

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

CopilotKit/CopilotKit · 46 tokens

copilotkit-upgrade

Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.

CopilotKit/CopilotKit · 48 tokens