usdkit-runtime-developer

A guide for editing USD 3D scene data in a running Swift application with USDKit on visionOS, macOS, or iOS 27. USD is a format and system for describing 3D scenes and their objects.

In plain words
What is it for?
Use it to open or create USD stages and layers, change 3D object properties, observe scene changes, export runtime USD packages, or connect a live stage to RealityKit.
Why use it?
It helps developers choose between changing a scene while the app runs and using command-line tools to edit or validate authored files.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tomkrikorian/visionosagents/usdkit-runtime-developer
Any agent
npx skills add tomkrikorian/visionOSAgents --skill usdkit-runtime-developer
Clone the repo
git clone --depth 1 https://github.com/tomkrikorian/visionOSAgents

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00075 $0.00649
Opus 5 $0.00037 $0.00324
Sonnet 5 $0.00015 $0.00130
Haiku 4.5 $0.00007 $0.00065

Measured 3d ago against content hash 57ed0e38e0e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

usdkit-runtime-developer 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.

skills/usdkit-runtime-developer/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

USDKit Runtime Developer

Quick Start

Use this skill for in-process USD stage work from Swift. For hand-authored .usda edits, package inspection, CLI conversion, or usdchecker validation, switch to $usd-editor.

  1. Confirm the target uses the 27 SDKs and can import USDKit.
  2. Decide whether the task belongs to runtime USDKit or the usd* command-line asset pipeline.
  3. Load the USDKit decision reference, then the USDKit framework reference.
  4. Keep USDStage, USDPrim, USDLayer, and nested property work on one actor; these types are not Sendable.
  5. For live RealityKit display, use USDStageComponent from the RealityKit skill; for Spatial Preview streaming, keep $spatial-preview-developer.

Load References When

Reference When to Use
usdkit-vs-cli.md When choosing between runtime USDKit and the command-line USD pipeline.
usdkit-framework.md When using USDStage, USDPrim, USDLayer, observers, export, or package APIs.
visionos-runtime-loading.md When checking how authored USD or USDZ content loads inside a visionOS app.
apple-runtime-boundaries.md When deciding whether to edit authored USD, load through RealityKit, or validate for Apple platforms.

Workflow

  1. Identify the owner: runtime Swift-edited stage, authored asset, or package pipeline.
  2. Use USDKit for in-process stage editing, observation, live rendering, or runtime package export.
  3. Keep CLI validation in the asset pipeline; USDKit does not replace usdchecker --arkit --strict.
  4. Preserve authored assets as source of truth unless the task is explicitly procedural or runtime-generated.

Guardrails

  • Do not use USDKit just to inspect or batch-convert files in CI; use the CLI tools through $usd-editor.
  • Do not assume beta USDKit symbols are stable; re-check the installed 27 SDK before shipping.
  • Do not recreate authored Reality Composer Pro content in Swift unless the feature explicitly requires procedural authoring.

Read the full file on GitHub · 59 lines

Files

What ships with it

5 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. 3d ago First seen · 59 lines · 75 tokens per session scan A 57ed0e38e0e0

Subscribe to this mod's changes

usdkit-runtime-developer is a skill published in the GitHub repository tomkrikorian/visionOSAgents (60 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 649 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

gamified-app

A multi-frame gamified mobile-app prototype — three phone frames on a dark showcase stage. Frame 1: cover / poster, Frame 2: today's quests with XP ribbons and a level bar, Frame 3: quest detail. Vivid quest tiles, level ribbon, bottom tab bar. Use when the brief asks for a "gamified app", "habit tracker", "RPG-style…

nexu-io/open-design · 117 tokens

mobile-games

Mobile game development principles. Touch input, battery, performance, app stores.

vudovn/ag-kit · 18 tokens

build-mobile-threejs-games

Build, tune, or test a Three.js game for mobile web. Use for touch movement, action controls, target selection, touch inventory, safe areas, portrait/landscape layouts, responsive HUD, battery/performance budgets, and real mobile browser QA.

MengTo/Skills · 57 tokens

building-mobile-game

Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…

Intelligent-Internet/ii-agent · 91 tokens

hz-android-2d-porting

Guides porting existing Android 2D apps to Meta Quest and Horizon OS — input adaptation, panel layout, and design requirements. Use when adapting a mobile Android app for Quest.

meta-quest/agentic-tools · 46 tokens

hz-new-project-creation

Scaffolds new Meta Quest and Horizon OS projects with recommended settings for Unity, Unreal, Android/Spatial SDK, or WebXR. Use when creating a new Quest app from scratch.

meta-quest/agentic-tools · 43 tokens