auto-rig

auto-rig is a skill for Claude Code, Codex from nirholas/three.ws. It costs 123 tokens per session (878 once invoked), scanned A, original, Apache-2.0.

A 3D character tool that adds a humanoid skeleton and movement controls to a GLB model, a common 3D file format, or creates a rigged avatar from text or images.

In plain words
What is it for?
It helps auto-rig GLB files and create avatars that can play idle or walking animations.
Why use it?
It makes static character models ready for animation without requiring manual skeleton and skin-weight setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Part of the three-ws-3d plugin — 4 skills shipped together

Good fit It helps auto-rig GLB files and create avatars that can play idle or walking animations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nirholas/three.ws/auto-rig
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 nirholas/three.ws --skill auto-rig
Clone the repo
git clone --depth 1 https://github.com/nirholas/three.ws

Made for: Claude Code, Codex.

Or install three-ws-3d, the plugin that ships this one along with the rest of its 4 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 auto-rig

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/three.ws/auto-rig.svg)](https://agentmods.dev/skills/nirholas/three.ws/auto-rig)
Your own site
<a href="https://agentmods.dev/skills/nirholas/three.ws/auto-rig"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/auto-rig.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 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 $0.00123 $0.00878
Opus 5 $0.00062 $0.00439
Sonnet 5 $0.00025 $0.00176
Haiku 4.5 $0.00012 $0.00088

Measured 3d ago against content hash 7168a88577d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

auto-rig 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 3d 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.

marketplace/plugins/three-ws-3d/skills/auto-rig/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Rig — skeleton + skin weights for animation

Two paths, depending on whether you already have a mesh.

Tools

Both on the three.ws MCP server (@three-ws/mcp-server).

rig_mesh — rig an existing GLB ($0.20 USDC)

Auto-rig a static GLB: adds a humanoid skeleton and per-vertex skin weights via the three.ws rig pipeline (Make-It-Animatable by default).

Param Required Notes
glb_url yes http(s) URL to the static GLB to rig — e.g. the glbUrl returned by forge-3d (forge_free), mesh-forge, or text-to-avatar.

Returns the rigged glbUrl and a three.ws pose-studio link (https://three.ws/forge?action=rig...) where the model plays the canonical idle/walk clip library.

forge_avatar — text/image → rigged avatar in one call ($0.45 USDC)

Chains the whole pipeline: Granite prompt director → FLUX + TRELLIS/Hunyuan3D mesh → Make-It-Animatable auto-rig, so the model loads straight into the pose studio.

Param Required Notes
prompt one of prompt/images A single humanoid character, e.g. "a friendly cartoon astronaut in a glossy white suit".
image_url / image_urls one of prompt/images Single image, or 1–4 angles (front/back/left/right) for higher-fidelity reconstruction.
direct no Run the Granite prompt-director stage (text mode). Default true.
aspect_ratio no Reference aspect ratio (text mode). Default 3:4 (portrait — best for a full-body figure).
allow_non_humanoid no Off by default. A clearly non-humanoid subject (furniture, vehicle, quadruped) is rejected without charge. Set true only to force-rig a non-character.

Returns the rigged glbUrl, the intermediate mesh URL, a pose-studio link, the directed prompt, and per-stage timing. You are not charged if no rigged avatar is produced.

Which to use

  • Already have a GLB (from forge-3d, mesh-forge, text-to-avatar, or the user's own file) → rig_mesh ($0.20).
  • Starting from just a prompt or photos and want it rigged → forge_avatar ($0.45, generation + rig bundled).

Read the full file on GitHub · 54 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. 3d ago First seen · 54 lines · 123 tokens per session scan A 7168a88577d8

Subscribe to this mod's changes

auto-rig is a skill published in the GitHub repository nirholas/three.ws (111 stars, last pushed today), licensed Apache-2.0. It adds 123 tokens to every session and 878 once invoked, about $0.0006 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 2026-09-03.

Related

Other skills, from other repositories

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

raphaelmansuy/edgecrab · 53 tokens

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

ibragimov-oasis/vibe-coder · 53 tokens

img2threejs

Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

img2threejs/img2threejs · 63 tokens

3d-asset-quality

Model what a 3D object is, not merely its outline, and prove quality with geometry-only close-up renders plus a manifest. Use before building, generating, importing, cleaning, reviewing, or signing off on meshes, props, buildings, terrain, environments, levels, dioramas, and set dressing in Blender, game engines, glTF…

RemakeBench/skills · 107 tokens

blender-mcp

Drive Blender via the catalog blender MCP, with bpy recipes.

GGbond-bo/MemOmics-Agent · 17 tokens

blender-physics

Blender rigid body, soft body, cloth, collision, force fields, particle systems, constraints, and simulation cache tools.

dcc-mcp/dcc-mcp-blender · 29 tokens