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.
npx skills add nirholas/three.ws --skill text-to-avatargit clone --depth 1 https://github.com/nirholas/three.wsWrote 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.
[](https://agentmods.dev/skills/nirholas/three.ws/text-to-avatar)<a href="https://agentmods.dev/skills/nirholas/three.ws/text-to-avatar"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/text-to-avatar.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.00687 |
| Opus 5 | $0.00046 | $0.00344 |
| Sonnet 5 | $0.00019 | $0.00137 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
text-to-avatar 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text → Avatar
Generate a high-quality textured 3D avatar from a description or one to four reference photos.
Tool
text_to_avatar (three.ws MCP server, @three-ws/mcp-server).
- Lane: PAID — $0.15 USDC per call, settled automatically over x402. Requires a funded wallet on the MCP transport (the
MCP_SVM_PAYMENT_ADDRESSthe plugin wires). If no payment payload is attached, the tool returns aPaymentRequiredstructured result describing what to pay. - Backend: Replicate (Hunyuan-3D 3.1 by default), polled synchronously until a GLB is produced or the timeout fires.
When to use this vs. the alternatives
- Free draft, text only: use
forge-3d(forge_free) — no payment. - Static avatar, prompt or photo, best texture: this skill (
text_to_avatar). - One-call rigged avatar ready to animate: use
auto-rig(forge_avatar) — it generates and rigs in a single call.
Inputs
| Param | Required | Notes |
|---|---|---|
prompt |
one of prompt/images | Natural-language description of the avatar (≤1000 chars). |
images |
one of prompt/images | 1–4 reference image URLs. When provided, the model does image-to-3D reconstruction. |
texture |
no | Request PBR textures when supported (default true). |
seed |
no | Integer seed for reproducible output. |
Outputs
glbUrl— the generated avatar.glb.- the source prompt/images, the picked model version, the Replicate prediction id, and timing metadata.
- Render or share it live with the
avatarserver's inline-render / embed-iframe tools, or openhttps://three.ws/viewer?src=<glbUrl>.
How to run
- Decide text vs image mode from the user's request. Gather
promptand/orimages(public http(s) URLs). - Call
text_to_avatar. If it returnsPaymentRequired, surface the price ($0.15 USDC) and how to fund — do not retry blindly. - Return
glbUrlplus a viewer/embed link. Offer to rig it (auto-rig→rig_mesh) so it can play the canonical idle/walk animations.
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.
- 4d ago First seen · 48 lines · 93 tokens per session scan A 3c02f876d70d
text-to-avatar is a skill published in the GitHub repository nirholas/three.ws (111 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 687 once invoked, about $0.0005 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.
Other skills, from other repositories
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.
blender-mcp
Control Blender directly from Gauss 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.
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.
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.
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.
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.