A workflow that rebuilds an object or character from a reference image as a procedural Three.js model, meaning a 3D model generated by code. It includes staged quality checks and visual correction.

Creating image-based 3D reconstructions, stylised or likeness-focused characters, sculpt specifications, and corrected preview renders.

It provides a code-based way to recreate reference images without extracting a mesh, using photogrammetry, or downloading art packs.

img2threejs — Skill for Codex by frabcd: A workflow that rebuilds an object or character from…

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.

agentmods

npx agentmods add skills/frabcd/codex-ai-game-studio/img2threejs

Any agent

npx skills add frabcd/codex-ai-game-studio --skill img2threejs

Clone the repo

git clone --depth 1 https://github.com/frabcd/codex-ai-game-studio

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/img2threejs.svg)](https://agentmods.dev/skills/frabcd/codex-ai-game-studio/img2threejs)

Your own site

<a href="https://agentmods.dev/skills/frabcd/codex-ai-game-studio/img2threejs"><img src="https://agentmods.dev/badge/skills/frabcd/codex-ai-game-studio/img2threejs.svg" alt="Measured on agentmods" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,477 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.06477
Opus 5	$0.00033	$0.03238
Sonnet 5	$0.00013	$0.01295
Haiku 4.5	$0.00007	$0.00648

Measured 6d ago against content hash 113de9657c4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

img2threejs 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 37 executable files (forge/_shared/artifact_cache.py, forge/_shared/color_metrics.py, forge/_shared/feature_acceptance_policy.py, …), 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/ai-game-studio-img2threejs/skills/img2threejs/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

img2threejs — Image to procedural Three.js

Rebuild the object visible in a reference image as a code-only procedural Three.js model, gated by a staged sculpting pipeline and an AI-vision self-correction loop. This is reconstruction-by-code, not photogrammetry, mesh extraction, or downloaded art packs.

Use Codex-native image reading, an already-enabled browser tool, the project preview, or a user-supplied screenshot wherever this workflow calls for agent vision or a browser.

Runtime and paths

Resolve SKILL_ROOT to the directory containing this SKILL.md. When Codex exposes PLUGIN_ROOT, this skill is at ${PLUGIN_ROOT}/skills/img2threejs; otherwise use the skill's discovered absolute path. Run every bundled script by absolute path from SKILL_ROOT and keep generated specifications, renders, and models in the user's project or an approved output directory, never in the installed plugin.

Use the active Python 3.10+ executable: py -3 or python on Windows, and python3 or the configured environment's interpreter on macOS. Pass arguments as an array and do not build a shell command. In command examples, <python> means that selected executable and <skill-root> means the resolved absolute SKILL_ROOT. The harness itself uses only the standard library.

The local specification index never writes into the installed plugin. Use --cache-root <approved-path> or AI_GAME_STUDIO_CACHE_DIR; otherwise a bounded OS user-cache directory is used. Generated specifications, code, renders, and evidence still belong in the approved project/output directory.

The built-in pixel tools decode compatible PNG directly. Common JPEG/TIFF/BMP inputs may be converted through the fixed native Windows System.Drawing or macOS /usr/bin/sips route. A non-native ImageMagick fallback is allowed only when AI_GAME_STUDIO_IMAGEMAGICK_MANIFEST points to a confirmed JSON record containing its absolute executable, SHA-256, version, reviewed license, HTTPS source URL, and plan digest. Unsupported formats must stop with a conversion request; never run an executable selected only from PATH.

Read the full file on GitHub · 350 lines

Files

What ships with it

60 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.

6d ago First seen · 350 lines · 66 tokens per session scan A 113de9657c4a

Subscribe to this mod's changes

img2threejs is a skill published in the GitHub repository frabcd/codex-ai-game-studio (9 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 6,477 once invoked, about $0.0003 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.

3d-animation Creative and media Game development agent-skills ai-agents ai-game-development blender codex-plugin

game-build

Build a risk-matched whitebox or the approved production game for its target runtime. Turn GAMEDESIGN, and ARTDIRECTION when production begins, into a minimal BUILDBRIEF and a runnable candidate that can be iterated with replayable evidence. Use for prototype the riskiest design question, implement the approved game…

zenstory-ai/novel-to-game · 151 tokens

game-concept

Design game concepts from a novel. From SOURCEBIBLE and PRODUCTBRIEF, generate three genuinely different directions on the dimensions still unlocked, then pick the most worthwhile playable prototype using hard vetoes and explicit trade-offs. Use for what game should this novel become, compare game concepts, choose a…

zenstory-ai/novel-to-game · 149 tokens

game-qa

Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed outcome, restart, and explicit limitations without dressing subjective fun up as a certain verdict. Use for test a generated game, QA a game build, check whether the…

zenstory-ai/novel-to-game · 146 tokens

3d_scene

Choose how to build a 3dscene asset. Do not default to one pipeline for every task: what the user specified about the scene's appearance matters more than the scene type, and generative reconstruction is the least stable route here.

OpenDCAI/GameFactory-3A · 0 tokens

cinematic-cutscene

Use when generating a non-interactive cutscene clip — opening scene, story beat, character intro, ending. Locks the look with a reference image, image-to-videos a 5-10s shot, optionally adds TTS dialogue, and wires it as a VideoStreamPlayer that fades in/out. Trigger on "cutscene", "intro cinematic", "opening scene"…

SummerEngine/summer-engine-agent · 105 tokens

lightning

Use when authoring a lightning bolt visual effect — procedural jagged path drawn via ImmediateMesh, glow shader, sparks at endpoints, screen shake. Trigger on "lightning bolt", "chain lightning", "electric attack", "tesla coil", "shock spell", "thunderbolt", "energy beam".

SummerEngine/summer-engine-agent · 65 tokens