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 agentmods add rules/tim0320/isaacsim-mcp/cursorrulesgit clone --depth 1 https://github.com/Tim0320/IsaacSim-MCPWhat 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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
cursorrules 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 yesterday.
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.
This is a copy
100% identical to cursorrules — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isaac Sim MCP Rules
General Rules
- Before executing any code, always check if the scene is properly initialized by calling get_scene_info()
- When working with robots, try using create_robot() first before using execute_script()
- If execute_script() fails due to communication error, retry up to 3 times at most
- For any creation of robot, call create_physics_scene() first
- Always print the formatted code into chat to confirm before execution
Physics Rules
- If the scene is empty, create a physics scene with create_physics_scene()
- For physics simulation, avoid using simulation_context to run simulations in the main thread
- Use the World class with async methods for initializing physics and running simulations
- When needed, use my_world.play() followed by multiple step_async() calls to wait for physics to stabilize
- SingleArticulation.initialize() requires World.physics_sim_view to be non-None. The adapter's play() and create_action_graph() call _ensure_physics_world() to guarantee this. When user presses Play from UI, the script must do its own World + initialize_physics() in a warmup phase.
Robot Creation Rules
- Before creating a robot, verify availability of connection with get_scene_info()
- Available robot types: "franka", "frankafr3", "jetbot", "carter", "g1", "go1" (use list_available_robots for full list)
- Position robots using their appropriate parameters
- For custom robot configurations, use execute_script() only when create_robot() is insufficient
Physics Scene Rules
- Objects should include 'type' and 'position' at minimum
- Object format example: {"path": "/World/Cube", "type": "Cube", "size": 20, "position": [0, 100, 0]}
- Default gravity is [0, 0, -981.0] (cm/s^2)
- Set floor=True to create a default ground plane
Script Execution Rules
- Use World class instead of SimulationContext when possible
- Initialize physics before trying to control any articulations
- When controlling robots, make sure to step the physics at least once before interaction
- For robot joint control, first initialize the articulation, then get the controller
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.
- yesterday First seen · 61 lines · 775 tokens per session scan A a13db8a54c91
cursorrules is a cursor rule published in the GitHub repository Tim0320/IsaacSim-MCP (0 stars, last pushed yesterday), licensed MIT. It adds 775 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursorrules, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
mod-001-use-physicsnemo-module-as-base-class
All model and layer classes must inherit from physicsnemo.Module (not torch.nn.Module directly) to ensure proper serialization, versioning, and registry functionality.
sounio
Sounio language rules — epistemic types, effects, algebra, GPU programming.
unity-performance
Cursor rule "unity-performance" from Common-ka/ai-agent-unity-rules, covering unity performance rules, update/fixedupdate/lateupdate, usage rules, object pooling (unityengine.pool) and addressables (not resources).
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.