openusd-architect

openusd-architect is a skill for Claude Code from qfoldit/Protein-Design-MCP. It costs 112 tokens per session (834 once invoked), scanned A, original, Apache-2.0.

A converter that turns a Universal Assembly Graph, a structured plan for a 3D scene and its interactions, into an OpenUSD scene for NVIDIA Omniverse. OpenUSD is a format and software ecosystem for describing complex 3D worlds.

In plain words
What is it for?
Use it to create USD stages and Omniverse scenes from UAG plans, including scene objects, relationships, extensions, user interfaces, and physics-related work.
Why use it?
It provides a documented route from an engine-neutral scene plan to USD and Omniverse tools without having to recreate the scene structure manually.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the qfoldit-skills plugin — 20 skills shipped together

Good fit Use it to create USD stages and Omniverse scenes from UAG plans, including scene objects, relationships, extensions, user interfaces, and physics-related work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qfoldit/protein-design-mcp/openusd-architect
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 qfoldit/Protein-Design-MCP --skill openusd-architect
Clone the repo
git clone --depth 1 https://github.com/qfoldit/Protein-Design-MCP

Made for: Claude Code.

Or install qfoldit-skills, the plugin that ships this one along with the rest of its 20 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 openusd-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/openusd-architect/github.svg)](https://agentmods.dev/skills/qfoldit/protein-design-mcp/openusd-architect)
Your own site
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/openusd-architect"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/openusd-architect/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 openusd-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/openusd-architect"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/openusd-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00112 $0.00834
Opus 5 $0.00056 $0.00417
Sonnet 5 $0.00022 $0.00167
Haiku 4.5 $0.00011 $0.00083

Measured 10d ago against content hash 35d3281780c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

openusd-architect scanned grade A 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Health checks: `curl localhost:8001/v1/health` (embedder), `:8002/v1/health` (reranker), `:9903/health` (USD Code MCP itself).
claude-skills/skills/openusd-architect/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openusd-architect

Status: official. Built on NVIDIA-Omniverse/kit-usd-agents, published directly by the NVIDIA-Omniverse GitHub organization.

Available official tooling

  • USD Code MCP -- 7 specialized tools for USD/OpenUSD API help: list_usd_modules, list_usd_classes, get_usd_module_detail, get_usd_class_detail, get_usd_method_detail, search_usd_code_examples (a 7th tool exists per the docs but wasn't confirmed by name -- check source/mcp/usd_code_mcp/README.md). Same principle as unigine-simulation-engineer: use these to verify USD API signatures rather than guessing, the API surface is large and easy to misremember.
  • Kit MCP / OmniUI MCP -- extension and UI-framework work.
  • Chat USD -- runs inside Omniverse Kit itself for natural-language scene interaction (not a standalone MCP server).
  • NVIDIA Skills (alternative to running the full MCP Docker stack): Omniverse RTX SDK, USD physics simulation, Kit development assistant, USD/OpenUSD development assistant, OmniUI development assistant -- also distributed via the Claude Code marketplace and Vercel Skill Marketplace (Physical AI section). Simpler to install than the full server stack if only reference info (not live execution) is needed.

UAG -> USD mapping

Baseline from game-designer/references/uag_schema.md: node -> USD prim under an Xform, type: mesh -> geometry prim (e.g. UsdGeomMesh), type: light -> UsdLuxLight subtype, parent_child -> SdfPath hierarchy, physics_collision -> UsdPhysics schema.

Local setup (if live MCP execution is needed, not just reference)

export NVIDIA_API_KEY=...   # required
export NGC_API_KEY=...      # only if pulling NIM containers for fully local models
cd source/mcp && ./build-wheels.sh all
docker compose -f docker-compose.local.yaml up --build   # cloud embed/rerank endpoints, faster start
# or: docker-compose.ngc.yaml for fully local NIM models (needs 1-2 NVIDIA GPUs)

Health checks: curl localhost:8001/v1/health (embedder), :8002/v1/health (reranker), :9903/health (USD Code MCP itself).

Read the full file on GitHub · 38 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. 10d ago First seen · 38 lines · 112 tokens per session scan A 35d3281780c2

Subscribe to this mod's changes

openusd-architect is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 112 tokens to every session and 834 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories