autonomous-3d-studio

autonomous-3d-studio is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 54 tokens per session (3,979 once invoked), scanned B, original, Apache-2.0.

A workflow for creating and preparing 3D models and materials, including sculpting, UV mapping, texturing, baking, and engine integration. UV mapping lays a 2D texture layout over a 3D model, while baking transfers detail between model versions.

In plain words
What is it for?
It helps model, retopologize, unwrap, texture, bake, inspect, and export 3D assets, including procedural geometry and USD-based scene composition.
Why use it?
It brings many production steps and quality checks into one process, helping prepare assets for games, films, and tools such as Blender or Unreal Engine.

Skill for Claude CodeCodex

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

Good fit It helps model, retopologize, unwrap, texture, bake, inspect, and export 3D assets, including procedural geometry and USD-based scene composition.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/autonomous-3d-studio
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 jxoesneon/Ciel --skill autonomous-3d-studio
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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 autonomous-3d-studio

README.md
[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-3d-studio/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/autonomous-3d-studio)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/autonomous-3d-studio"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-3d-studio/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 autonomous-3d-studio

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/autonomous-3d-studio"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/autonomous-3d-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,979 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00054 $0.03979
Opus 5 $0.00027 $0.01989
Sonnet 5 $0.00011 $0.00796
Haiku 4.5 $0.00005 $0.00398

Measured 6d ago against content hash 404276d19097, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

autonomous-3d-studio scanned grade B with 1 finding 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 22 executable files (assets/blender_mcp_addon.py, scripts/autonomous_refinement_loop.py, scripts/blender_mcp_server.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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| [`scripts/blender_mcp_server.py`](file://~/.gemini/config/skills/autonomous-3d-studio/scripts/blender_mcp_server.py) | Live Blender MCP & TCP socket RPC bridge for interactive real-time viewport and scene control | `py
skills/autonomous-3d-studio/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous 3D Studio — AAA+ Production Engine

autonomous-3d-studio is CIEL's comprehensive, deepest-in-class autonomous 3D pipeline orchestration skill. It empowers agents to execute end-to-end 3D asset creation at AAA+ game studio and cinematic film VFX standards.

The skill provides live Blender MCP viewport bridging, deterministic headless execution harnesses, strict geometric QA gates, automated multi-angle visual inspection, mathematical UV and texel density optimization, 16/32-bit high-to-low baking, procedural geometry node construction, MaterialX/OpenPBR shader graphs, Substance SAT integration, QuadriFlow retopology, seamless Unreal Engine 5 / USD integration, and closed-loop self-repair loops.


1. The 7-Stage AAA Production Pipeline

Every 3D asset created under this skill strictly adheres to the 7-Stage End-to-End Pipeline:

┌──────────────────────────────────────────────────────────────────────────────────────────────────┐
│                               7-STAGE AAA 3D PRODUCTION PIPELINE                                 │
├─────────────────┬─────────────────┬─────────────────┬──────────────────┬─────────────────────────┤
│ STAGE 1         │ STAGE 2         │ STAGE 3         │ STAGE 4          │ STAGE 5                 │
│ Concept & High- │ Topology &      │ UV Unwrapping & │ Cage Prep & High-│ PBR & MaterialX         │
│ Poly Sculpting  │ Retopology      │ Packing         │ to-Low Baking    │ Authoring               │
├─────────────────┼─────────────────┼─────────────────┼──────────────────┼─────────────────────────┤
│ • SubD / CAD    │ • Quad flow     │ • Seam math     │ • Averaged cage  │ • Metal/Rough PBR       │
│ • Voxel / Dyntopo│ • Pole control  │ • Texel density │ • 16-bit Normal  │ • OpenPBR / MatX        │
│ • AI-3D cleanup │ • Deform loops  │ • 0% overlap    │ • AO & Curvature │ • Channel packing       │
│ • Micro-bevels  │ • Nanite/LODs   │ • UDIM tiles    │ • ID & Bent Norm │ • Smart layers          │
└────────┬────────┴────────┬────────┴────────┬────────┴────────┬─────────┴────────────┬────────────┘
         │                 │                 │                 │                      │
         ▼                 ▼                 ▼                 ▼                      ▼
┌──────────────────────────────────────────────────────────────────────────────────────────────────┐
│ STAGE 6: Rigging, Skinning & Blendshapes  │ STAGE 7: Engine Integration & Scene Assembly         │
├───────────────────────────────────────────┼──────────────────────────────────────────────────────┤
│ • Bone roll alignment & IK/FK chains      │ • Unreal Engine 5 Nanite, Lumen & LODs               │
│ • Dual-Quaternion / Heat-diffuse weights │ • OpenUSD (UsdGeomMesh, UsdShade) Stage Assembly     │
│ • FACS 52 Facial Blendshape deltas        │ • UCX/UBX Chaos Collision Hulls & Physics Setup      │
└───────────────────────────────────────────┴──────────────────────────────────────────────────────┘

Read the full file on GitHub · 158 lines

Files

What ships with it

39 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 First seen · 158 lines · 54 tokens per session scan B 404276d19097

Subscribe to this mod's changes

autonomous-3d-studio is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 3,979 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.