A browser-based tool for teleoperating supported robots, meaning controlling them remotely through a web interface. It records immutable LeRobot datasets and supports custom bundles and PAIDF exports, where PAIDF is a physical-AI data format.

Use it to operate the supported SO101 robot tasks in a browser, record LeRobot data, work with custom bundles, and export or materialize PAIDF data.

It brings robot control, secure agent communication, and recording into one supported workflow. It also defines which robot tasks, environments, and hardware are currently supported.

leisaac — Skill for Codex by nebius

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 nebius/nebius-physical-ai --skill leisaac

Clone the repo

git clone --depth 1 https://github.com/nebius/nebius-physical-ai

Made for: Codex.

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/skills/nebius/nebius-physical-ai/leisaac/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/leisaac)

Your own site

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/leisaac"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/leisaac/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/skills/nebius/nebius-physical-ai/leisaac"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/leisaac.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,051 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00051	$0.03051
Opus 5	$0.00026	$0.01525
Sonnet 5	$0.00010	$0.00610
Haiku 4.5	$0.00005	$0.00305

Measured 4d ago against content hash f4a86342cf41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

leisaac 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.

skills/tools/leisaac/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LeIsaac browser teleoperation

Use this skill for the real LightwheelAI/LeIsaac workbench service and its authenticated NPA agent UI. Read docs/workbench/leisaac-teleoperation.md and docs/workbench/guides/leisaac-transport-latency.md before changing runtime, transport, recorder, or UI behavior.

Also load these skills when their surfaces are involved:

third-party-eula-preflight, gpu-selection, and nebius-infra before a live launch;
npa-agent and agent-fresh-operate for agent deployment or live UI tests;
workbench-tool, testing-conventions, real-components, and solution-licensing for implementation, validation, or packaging changes;
physical-ai-data-factory for PAIDF export or materialization.

Ground truth and capability boundary

Source is LeIsaac 0.4.0 at 1651c321e9b0c1bb54233211fc7b3cd70d8373d5 with exact, build-gated NPA packaging and observability patches.
The supported real tasks are LeIsaac-SO101-PickOrange-v0 and LeIsaac-SO101-LiftCube-v0. Browser operation uses upstream SO101Keyboard; one session controls exactly one environment.
Rendering requires RT cores. The current launcher supports only the named RTX PRO 6000 Kubernetes pool. Do not route this workload to H100/H200, and do not advertise L40S until this exact image and launch path are validated.
Isaac Sim/Lab, NVIDIA's browser client, SO-101, and scene assets are runtime-fetched only after the shared Isaac preflight. The single public input defaults ACCEPT_EULA=Y; Y, YES, 1, and TRUE normalize to Y, while empty, N, NO, 0, and FALSE explicitly opt out before download and other values are invalid. The runtime derives OMNI_KIT_ACCEPT_EULA=YES internally. Do not add duplicate public consent variables or prompts. Keep PRIVACY_CONSENT and telemetry off by default.
This is a lifecycle-bearing interactive service, not a finite npa.workflow step. Launch and destroy it with the workbench CLI.

Security and transport decision

Read the full file on GitHub · 254 lines

Files

What ships with it

1 file 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 202 B

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.

4d ago Changed · +30 lines f4a86342cf41
10d ago First seen · 224 lines · 51 tokens per session scan A a7f10f65ca00

Subscribe to this mod's changes

leisaac is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 3,051 once invoked, about $0.0003 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.

Hardware and IoT

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens