3d_scene

3d_scene is a skill for Claude Code, Codex from OpenDCAI/GameFactory-3A. It costs 0 tokens per session (3,581 once invoked), scanned A, original, Apache-2.0.

A decision guide for choosing how to create a 3D scene, such as an environment or game level. It considers the desired appearance and may favor licensed existing assets or a reconstruction workflow.

In plain words
What is it for?
Use it when planning a 3D scene for engines such as Unreal, Unity, Godot, Blender, or three.js.
Why use it?
It helps avoid using the same asset-making method for every scene and accounts for appearance, stability, import paths, and licensing.

Skill for Claude CodeCodex

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

Good fit Use it when planning a 3D scene for engines such as Unreal, Unity, Godot, Blender, or three.js.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendcai/gamefactory-3a/3d_scene
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 OpenDCAI/GameFactory-3A --skill 3d_scene
Clone the repo
git clone --depth 1 https://github.com/OpenDCAI/GameFactory-3A

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 3d_scene

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/3d_scene.svg)](https://agentmods.dev/skills/opendcai/gamefactory-3a/3d_scene)
Your own site
<a href="https://agentmods.dev/skills/opendcai/gamefactory-3a/3d_scene"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/3d_scene.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,581 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 $0.00000 $0.03581
Opus 5 $0.00000 $0.01791
Sonnet 5 $0.00000 $0.00716
Haiku 4.5 $0.00000 $0.00358

Measured yesterday against content hash b3e6e1d0438c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

3d_scene 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 yesterday.

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.

agent_skills/asset_qa/3d_scene/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate 3D Scene — Strategy Skill

Choose how to build a 3d_scene 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.

Decision

Ask first: did the user specify the scene's 3D appearance?

Situation Prefer Why
Appearance not specified — no reference image, no described look Downloadable, licence-checked assets. Search the selected engine's own asset library for a usable scene or environment kit: UE5 (Fab / Marketplace, Quixel), Unity (Asset Store, packages), Godot (Asset Library), Blender (bundled assets, CC0 libraries), three.js (curated CC0 packs — see <REPO_PATH>/agent_skills/engine_context/three_js_api.md) Nothing constrains the look, so a licensed, artist-made scene is more shippable than anything generated, and it imports through a documented path. Record source and licence
Appearance specified — reference image or a described look Lay out the terrain/ground first, then add foreground objects (see Ground first, then objects below, and Scene construction code chain for the mechanised form) WorldPlay-style reconstruction is not yet stable enough to be the default. Ground + placed props is controllable, editable, and reproduces a requested look reliably
Appearance specified, the space is indoor/enclosed, and the user needs high fidelity WorldPlay-style reconstruction This is the one case where the reconstruction path earns its instability: an enclosed volume has no horizon or sky to break, and one reference image can carry the whole interior

Prefer downloadable assets even when the appearance is specified, if a library scene already matches the requested look — generation is not a goal in itself.

Do not silently switch strategies. State which row you selected and why, and if the user asked for the reconstruction path outside the indoor high-fidelity case, say that it is the unstable route before spending time on it.

Read the full file on GitHub · 282 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. yesterday Changed · +148 lines b3e6e1d0438c
  2. 9d ago First seen · 134 lines · 0 tokens per session scan A 6f614a58531d

Subscribe to this mod's changes

3d_scene is a skill published in the GitHub repository OpenDCAI/GameFactory-3A (559 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,581 tokens. 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

alpha-scene-gen

Generates AI 3D models through the Alpha3D MCP connector and imports them directly into the user's currently open Blender scene, scaled and placed to build out a described environment, prop set, or character roster. Use this skill whenever the user wants to populate, build, dress, furnish, or fill a Blender scene with…

ig-shadow-walker/BlenderXAlpha-3DGenSkill · 284 tokens

meshy-3d-generation

Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…

meshy-dev/meshy-3d-agent · 101 tokens

meshy-openclaw

Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture…

meshy-dev/meshy-3d-agent · 128 tokens

blender-director

Use when starting any Blender asset task, planning a production pipeline, coordinating multiple disciplines, or matching a reference photo/concept art. Invoke for game-ready assets, hard surface, environment, character, creature, export, or any multi-skill Blender workflow.

arjun988/blender-skills · 56 tokens

environment-artist

AAA environment art for modular kits, buildings, terrain, vegetation, architecture, and scene composition. Use for game-optimized environments, storytelling through space, and modular asset pipelines in Blender via MCP.

arjun988/blender-skills · 43 tokens

hard-surface

AAA hard surface modeling for sci-fi, industrial, military, vehicles, weapons, robotics, and mechanical props. Use for boolean/bevel workflows, panel lines, greebles, chamfers, and manufacturing-accurate surfaces in Blender via MCP.

arjun988/blender-skills · 54 tokens