Borrowing it
Nothing to install: this file belongs to Tim0320/IsaacSim-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Tim0320/IsaacSim-MCP/main/.agents/skills/omniverse-windows-workspace/SKILL.mdgit clone --depth 1 https://github.com/Tim0320/IsaacSim-MCPWrote 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/tim0320/isaacsim-mcp/omniverse-windows-workspace)<a href="https://agentmods.dev/skills/tim0320/isaacsim-mcp/omniverse-windows-workspace"><img src="https://agentmods.dev/badge/skills/tim0320/isaacsim-mcp/omniverse-windows-workspace/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.
<a href="https://agentmods.dev/skills/tim0320/isaacsim-mcp/omniverse-windows-workspace"><img src="https://agentmods.dev/badge/skills/tim0320/isaacsim-mcp/omniverse-windows-workspace.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.01322 |
| Opus 5.5 | $0.00031 | $0.00529 |
| Sonnet 5.5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
omniverse-windows-workspace 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 2mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omniverse Windows Workspace
Classify the request first. Load only the checks and references that can change the result.
Choose the task route
| Task type | First action | Environment check |
|---|---|---|
| Documentation, architecture, research review, schema explanation | Read the requested source and authority rules. | Do not run by default. |
| Repository code, offline tests, refactor, docs generation | Inspect Git root/status and relevant files; preserve unrelated changes. | Run only if the change depends on Isaac/Kit imports, installed paths, GPU, ports, or live evidence. |
| Live Stage query or mutation | Read MCP routing, then run scripts/check-environment.ps1. |
Required. Verify the listener and read back every mutation. |
| Launcher, installation, runtime, GPU, extension, or port diagnosis | Read environment and MCP routing, then run the environment check. | Required. |
| Release or GitHub publish | Read the 6.x reference and release documentation; verify exact Git identity and backup first. | Required only when the gate or claim includes live/runtime verification. |
| Isaac Lab | Keep it separate from this Isaac Sim MCP repository; resolve its root and current version before editing. | Required for runtime work. |
The environment check reports state; it does not authorize installation, process changes, Stage writes, or publishing. Do not reinstall Isaac Sim, Isaac Lab, CUDA, Docker, or dependencies merely because a process is stopped.
Load the relevant capability reference
- 1.x: Camera, LiDAR, artifacts, and sensor lifecycle.
- 2.x: robot joints, drives, motion, grippers, mobile bases, and articulation/physics-tensor lifecycle recovery.
- 3.x: physics parameters, backend capability, authoring, materials, and Stage composition.
- 4.x: OmniGraph, ScriptNode, ROS 2, Replicator SDG, humans, Behavior Agents, and NavMesh.
- 5.x: script policy, command governance, idempotency, jobs, transport, and diagnostics.
- 6.x: test layers, scratch-stage safety, profile-aware generated inventory, evidence reports, migration, release gates, and publishing.
- V6 adapter runtime: read before changing
IsaacAdapterV6,v6_runtime, component state ownership, hot reload order, or the deferred Graph/ROS2/Replicator/Human boundary.
What ships with it
12 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 286 B
- references/environment.md 2.3 KB
- references/isaacsim-mcp-1x.md 8.0 KB
- references/isaacsim-mcp-2x.md 11 KB
- references/isaacsim-mcp-3x.md 8.7 KB
- references/isaacsim-mcp-4x.md 9.2 KB
- references/isaacsim-mcp-5x.md 10 KB
- references/isaacsim-mcp-6x.md 6.2 KB
- references/mcp-routing.md 2.5 KB
- references/v6-adapter-runtime.md 3.8 KB
- scripts/check-environment.ps1 5.5 KB runs code
- scripts/install-skill.ps1 1.1 KB runs code
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.
- 2mo ago First seen · 71 lines · 77 tokens per session scan A bcc72a06712d
omniverse-windows-workspace is a skill published in the GitHub repository Tim0320/IsaacSim-MCP (1 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 1,322 once invoked, about $0.0003 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 2026-08-31.
omniverse-windows-workspace compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| omniverse-windows-workspaceTim0320/IsaacSim-MCP | Skill | 1 | 5d ago | MIT | A | 77 | Codex |
| metal-shader-expertcuriositech/some_claude_skills | Skill | 264 | 4d ago | MIT | A | 121 | Claude Code |
| hz-unity-meta-movement-sdk-retargetingmeta-quest/agentic-tools | Skill | 248 | 1mo ago | Apache-2.0 | A | 186 | Claude Code |
| hz-unity-face-trackingmeta-quest/agentic-tools | Skill | 248 | 1mo ago | Apache-2.0 | A | 92 | Claude Code |
| hz-unity-meta-core-sdkmeta-quest/agentic-tools | Skill | 248 | 1mo ago | Apache-2.0 | A | 97 | Claude Code |
| kernelcad-sdformatw1ne/kernelCAD-web | Skill | 36 | today | MIT | A | 64 | Claude Code, Codex |
| hz-unity-passthrough-camera-accessmeta-quest/agentic-tools | Skill | 248 | 1mo ago | Apache-2.0 | A | 197 | Claude Code |