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 robium-ai/robium --skill isaac-simgit clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/isaac-sim)<a href="https://agentmods.dev/skills/robium-ai/robium/isaac-sim"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/isaac-sim.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 74 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 100 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 140 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Privilege Escalation · line 156 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Privilege Escalation · line 158 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Prompt Injection · line 227 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium MCP Rug Pull · line 156 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00125 | $0.04486 |
| Opus 5 | $0.00063 | $0.02243 |
| Sonnet 5 | $0.00025 | $0.00897 |
| Haiku 4.5 | $0.00013 | $0.00449 |
Grade A, and why
isaac-sim 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.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
isaac-sim
The NVIDIA-ecosystem entry point for robium: installing and containerizing
Isaac Sim, meeting its GPU/driver floor, building USD scenes, adding robots
and sensors, bridging to ROS 2, and running headless with livestreaming on a
remote server. Isaac Sim is a GPU-gated tool, not a default; the very first
thing this skill does, every time, is check whether the target machine can
run it at all. as of 2026-07-10 the current release is Isaac Sim
6.0.1 (the nvcr.io/nvidia/isaac-sim container tag and the isaacsim
PyPI package version track together), verified by direct fetch of
docs.isaacsim.omniverse.nvidia.com and the NGC catalog page on 2026-07-10;
see references/setup-and-requirements.md for exactly how each fact below
was checked. GPU/driver/OS requirements change per release; re-verify before
trusting a number here in a future session.
When to use this skill
- Installing or containerizing Isaac Sim, checking whether a machine meets its GPU/driver floor, building or loading a USD scene, adding a robot or sensor, wiring the ROS 2 bridge, or running headless/livestreamed on a remote box.
- The trigger phrases in the description: 'isaac sim', 'omniverse', GPU photorealistic simulation, synthetic data generation, NVIDIA robotics ecosystem work.
- Someone asks "should I use Isaac Sim or Gazebo?" before a GPU has been confirmed: answer the GPU question first (see Key directives), don't assume Isaac Sim is available.
- Cross-references: go to the sibling skill instead when the question is:
- Whether to use Isaac Sim at all vs. Gazebo or something else →
the
simulationskill (the architect skill's stack-selection reference carries the same decision tree). This skill assumes Isaac Sim has already been chosen. - No RTX-class GPU available →
gazebo. Don't try to make Isaac Sim work without the GPU floor; route away instead (see Key directives). - RL training at scale on top of Isaac Sim (parallel GPU
environments, policy training loops) →
isaac-lab. This skill stops at "the sim is running, a robot and sensors are in it, and data can be produced"; training loops areisaac-lab's territory. - Generic Docker/GPU-container mechanics (NVIDIA Container Toolkit
install,
--gpus all, CUDA-driver version matching, headless-display strategy in general) →environments. This skill's container guidance assumes that groundwork is already in place and covers only what's Isaac-Sim-specific on top of it. - Synthetic-data STRATEGY: which datasets/sources to combine, how
much synthetic vs. real data a project needs → the
dataumbrella skill. This skill owns the mechanics of generating synthetic data inside Isaac Sim (Replicator, writers, output formats); see Usage patterns. - ROS 2 mechanics beyond the bridge itself (workspaces, colcon,
launch files, TF2, QoS) →
ros2. This skill's ROS 2 content is limited to what the bridge extension publishes/subscribes. - Lightweight simulation, or a sim that doesn't need a GPU →
gazebo. - The whole-stack decision this feeds into →
architect(routes here, gated on the GPU floor).
- Whether to use Isaac Sim at all vs. Gazebo or something else →
the
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.
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 First seen · 298 lines · 125 tokens per session scan A 7d51b74a60d2
isaac-sim is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 9d ago), licensed MIT. It adds 125 tokens to every session and 4,486 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
agopengps-knowledge-patch
Use this skill when designing, extending, deploying, or diagnosing AgOpenGPS, AgIO, AgValoniaGPS, AgOpenWeb, GNSS correction paths, autosteer hardware, or machine-control hardware. Start by identifying the exact application release, codebase, board revision, firmware source commit, and operating mode.
sciomc
Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode.
aerospace-engineering-technician
Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…
automotive-engineering-technician
Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…
biomass-plant-technician
Use when a task needs the judgment of a Biomass Plant Technician — adjusting combustion parameters in response to actual measured fuel moisture content rather than a fixed setpoint, diagnosing a fuel feed interruption as mechanical bridging rather than a combustion issue, adjusting soot-blowing frequency to actual…
smarterweather-mcp
Install and use Smarter Weather's hosted MCP servers: the weather MCP (forecasts, alerts, radar/satellite imagery, and raw dataset queries) and the onboarding MCP (agent-first signup, API key minting, client configuration, usage and billing). Covers stdio bridge install for Cursor / Claude Code / VS Code, Streamable…