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 tomkrikorian/visionOSAgents --skill usd-editorgit clone --depth 1 https://github.com/tomkrikorian/visionOSAgentsWrote 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/tomkrikorian/visionosagents/usd-editor)<a href="https://agentmods.dev/skills/tomkrikorian/visionosagents/usd-editor"><img src="https://agentmods.dev/badge/skills/tomkrikorian/visionosagents/usd-editor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00082 | $0.01044 |
| Opus 5 | $0.00041 | $0.00522 |
| Sonnet 5 | $0.00016 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
usd-editor 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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
USD Editor
Quick Start
Use this skill for minimal, text-level USD or USDA edits and command-line USD inspection, conversion, packaging, rendering, and validation. Keep the change small and preserve existing composition unless the task explicitly says otherwise.
When authored Reality Composer Pro or USD content owns the scene, geometry, transform, animation, or material, keep that authored surface as the source of truth. Use Swift and RealityKit to load or adjust runtime state; do not recreate authored USD content in Swift unless the request is explicitly procedural.
If Swift code needs to open, edit, observe, or export stages in-process with
USDStage, USDPrim, or USDLayer, switch to $usdkit-runtime-developer.
If the change is material- or shader-specific for RealityKit, prefer
shadergraph-editor.
Load References When
| Reference | When to Use |
|---|---|
usd-syntax |
When you need a refresher on .usda syntax, values, and path formats. |
prims-properties |
When adding or editing prims, attributes, or relationships. |
composition-variants |
When touching sublayers, references, payloads, or variant sets. |
transforms-units |
When editing transforms, xformOps, or stage units and up-axis metadata. |
time-samples |
When modifying animated or time-sampled properties. |
command-line-tools |
When you need a quick reference for common USD command-line tools. |
usdcat |
When converting, flattening, or inspecting USD files. |
usdchecker |
When validating USD or USDZ assets, including RealityKit-focused checks. |
usdrecord |
When rendering images from USD files. |
usdtree |
When inspecting the prim hierarchy of a USD file. |
usdzip |
When creating or inspecting USDZ packages. |
usdedit |
When you need the official text-editing workflow for a USD-readable file. |
visionos-runtime-loading.md |
When the question is how authored USD or USDZ actually loads and behaves in a visionOS app. |
apple-runtime-boundaries.md |
When deciding whether to edit authored USD / Reality Composer Pro content, load it through RealityKit, or validate it for Apple platforms. |
What ships with it
17 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.
- agents/openai.yaml 374 B
- assets/studio-meije-logo-small.png 4.2 KB
- assets/studio-meije-logo.png 42 KB
- references/apple-runtime-boundaries.md 1.8 KB
- references/command-line-tools.md 778 B
- references/composition-variants.md 1.0 KB
- references/prims-properties.md 1.1 KB
- references/time-samples.md 460 B
- references/transforms-units.md 755 B
- references/usd-syntax.md 1.8 KB
- references/usdcat.md 1.1 KB
- references/usdchecker.md 2.1 KB
- references/usdedit.md 868 B
- references/usdrecord.md 1.3 KB
- references/usdtree.md 896 B
- references/usdzip.md 1.6 KB
- references/visionos-runtime-loading.md 1.3 KB
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.
- 8d ago First seen · 81 lines · 82 tokens per session scan A 0c4d5639601e
usd-editor is a skill published in the GitHub repository tomkrikorian/visionOSAgents (60 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,044 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.
Other skills, from other repositories
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.
threejs-audio-generator
Generate, convert, clean, and integrate audio for Three.js browser games with ElevenLabs: sound effects, looping ambience, UI sounds, impact/weapon/vehicle audio, creature and boss stingers, announcer and dialogue TTS, voice conversion from a scratch performance, voice cleanup, audio manifests, and Web Audio…
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
sprite-gen
Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…