A robotics simulation workflow for running, checking, and troubleshooting Enactic OpenArm workloads in MuJoCo and NVIDIA Isaac Sim or Isaac Lab. MuJoCo and Isaac Sim are software tools that simulate robots and physics.

It is for packaging and validating OpenArm simulations in the NPA workbench, including runs in both supported simulators.

It provides the required source versions, robot assets, simulator boundaries, and licensing checks for this specific robot workload.

openarm — Skill for Claude Code and Codex by nebius/nebius-physical-ai

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 openarm

Clone the repo

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

Made for: Claude Code, 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/openarm/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/openarm)

Your own site

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

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,188 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.

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	$0.00037	$0.01188
Opus 5.5	$0.00015	$0.00475
Sonnet 5.5	$0.00007	$0.00238
Haiku 4.5	$0.00004	$0.00119

Measured 1mo ago against content hash 0e517440d506, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openarm 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 1mo 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/openarm/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enactic OpenArm

Use the native npa workbench openarm surface and the workflows/testing/openarm-simulators.yaml reference workflow. Do not route OpenArm to the generic Isaac Lab or RoboCasa tools: the OpenArm tool owns the upstream source pins, robot assets, task IDs, artifact schemas, and dual-simulator qualification contract.

Legal and runtime boundary

Pin enactic/openarm_mujoco release 2.2.0 to commit a8c979629f2591ad035d99d338ce114969e6cddc.
Pin the untagged enactic/openarm_isaac_lab repository to commit bad82e23716e6941c2de78ccb978f57c78b37734.
Both simulator repositories and their included model assets are Apache-2.0. Do not copy hardware/CAD payload from the separate OpenArm repository.
The public image may bake OpenArm and MuJoCo OSS bytes. It must never bake Isaac Sim, Isaac Lab, Omniverse Kit, acceptance, credentials, caches, or data. Load and follow skills/atomic/third-party-eula-preflight/SKILL.md and skills/atomic/solution-licensing/SKILL.md before building or executing.
Invoke Isaac only through ${ISAAC_LAB_PYTHON:-/isaac-sim/python.sh}. Never run this shim from a Dockerfile RUN instruction.
Classify the CUDA base and CUDA/cuDNN Python runtime libraries as conditional NVIDIA redistributable components, not OSS. Retain their notices, remove separately installed SDK headers/static archives, and review their exact built-image files and SBOM before publication.

Supported workloads

MuJoCo uses the real upstream openarm_demo_xml, JointResolver, and mujoco.mj_step. A successful run uploads result.json and mujoco_trajectory.npz; --render adds a simulator-rendered MP4.

Isaac rollout imports openarm.tasks, creates the requested upstream OpenArm Gymnasium task, and performs real vectorized steps. Isaac training calls the pinned upstream RSL-RL script and fails closed unless a model_*.pt checkpoint exists. Isaac-Reach-OpenArm-v0 is the default qualification task. Treat lift, drawer, bimanual, imitation, teleoperation, and sim-to-real as unqualified until each has exact-image live evidence; upstream itself says the latter three are under development.

Read the full file on GitHub · 92 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.

1mo ago First seen · 92 lines · 37 tokens per session scan A 0e517440d506

Subscribe to this mod's changes

openarm is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,188 once invoked, about $0.0001 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 2026-09-17.

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

holoscan-install-wheel

Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.

NVIDIA/skills · 34 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

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

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