What is ovui AGENTS.md?

Repository instructions for NVIDIA Omniverse’s ovui user-interface project. They explain what the repository contains, where its main parts are, and how to perform common work in it.

Use them when exploring, modifying, building, or otherwise working in the ovui repository.

They give an agent the project background and working procedures needed to navigate the repository. This avoids relying on assumptions about its layout or development workflow.

How NVIDIA-Omniverse/ovui configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to NVIDIA-Omniverse/ovui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/NVIDIA-Omniverse/ovui/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-Omniverse/ovui

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nvidia-omniverse/ovui/agents-md/github.svg)](https://agentmods.dev/instructions/nvidia-omniverse/ovui/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nvidia-omniverse/ovui/agents-md"><img src="https://agentmods.dev/badge/instructions/nvidia-omniverse/ovui/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nvidia-omniverse/ovui/agents-md"><img src="https://agentmods.dev/badge/instructions/nvidia-omniverse/ovui/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,525 This file is loaded in full into every session.

When invoked 2,525 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02525	$0.02525
Opus 5.5	$0.01010	$0.01010
Sonnet 5.5	$0.00505	$0.00505
Haiku 4.5	$0.00252	$0.00252

Measured 24d ago against content hash b4da231028eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ovui AGENTS.md 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 24d 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.

AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - AI Agent Guide for ovui

This file gives AI coding agents the minimum context needed to work effectively in this repository. Use it as a starting map, then go to skills/ for task-level implementation guidance.

What This Repo Is

ovui is a Python UI framework, a library of ready-made app widgets, and a runnable reference application for building scene, viewport, and data tools. The repository ships:

a Python-facing UI layer (ovui, imported in Python as omni.ui and omni.ui_scene)
a library of composable app widgets (ovui-widgets/ - stage browser, property inspector, content browser, viewport, composition view)
data adapters that connect those widgets to OpenUSD or custom backends (ovui-data-adapters/)
a screenshot-first inspector pipeline that lets people and AI coding agents drive the running UI through the same screenshot-action loop

Primary use case: building polished, consistent scene, viewport, and data tools on top of OpenUSD and ovrtx.

Start Here

Read README.md for top-level product context.
Read docs/architecture.html (a TOC + iframe shell) and the per-section pages under docs/architecture/section-01.html ... docs/architecture/section-11.html for the architectural overview, the UI layer, the scene tools, ovui-widgets, adapters, the application, and the inspector pipeline.
Read skills/omniverse-ui-apis/SKILL.md, skills/omniverse-ui-widgets/SKILL.md, skills/omniverse-ui-styling/SKILL.md, and skills/omniverse-ui-inspector/SKILL.md to understand the repo's agent-facing skill surfaces before starting task-level work.

Repo Layout (High-Level)

ovui/ - Python UI framework source (the omni.ui and omni.ui_scene Python packages, C++ bindings, examples, headless mode, standalone runtime, markdown widget, and screenshots).
ovui-widgets/ - app widget library and the runnable reference application (USD Viewer), including stage browser, property inspector, content browser, viewport, composition view, common services, and the menu/file-open wiring.
ovui-data-adapters/ - OpenUSD-backed adapters (stage, property, transform, renderer) plus session authoring and livestream tap.
docs/architecture.html and docs/architecture/ - per-section architectural documentation (11 sections from project overview through the inspector pipeline) plus shared styles.
skills/ - Task-oriented agent skills (SKILL.md plus references/ per skill).
README.md, CHANGELOG.md, LIVESTREAM.md, VERSION.md - top-level product and process documentation.

Read the full file on GitHub · 102 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.

24d ago Changed · +1 lines · +30 tokens per session b4da231028eb
2mo ago First seen · 101 lines · 2,495 tokens per session scan A 564041a25b67

Subscribe to this mod's changes

ovui AGENTS.md is an instructions file published in the GitHub repository NVIDIA-Omniverse/ovui (55 stars, last pushed 24d ago), licensed Apache-2.0. It adds 2,525 tokens to every session, about $0.0101 per session on Opus 5.5. 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.

ovui AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ovui AGENTS.mdNVIDIA-Omniverse/ovui	Instructions file	55	24d ago	Apache-2.0	A	2,525	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ovui: Instructions file for Codex