PhysicsNeMo is an open-source PyTorch framework for creating, training, and fine-tuning machine-learning models for physics, scientific computing, and engineering. Researchers and engineers use its reusable components and training recipes for applications such as aerodynamics, weather forecasting, structural mechanics, geophysics, and thermal design. The catalogue entries provide rules and skills for working with PhysicsNeMo projects.
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.
git clone --depth 1 https://github.com/NVIDIA/physicsnemoWrote 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/rules/nvidia/physicsnemo/mod-003d-missing-required-method-docstring-sections)<a href="https://agentmods.dev/rules/nvidia/physicsnemo/mod-003d-missing-required-method-docstring-sections"><img src="https://agentmods.dev/badge/rules/nvidia/physicsnemo/mod-003d-missing-required-method-docstring-sections/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/rules/nvidia/physicsnemo/mod-003d-missing-required-method-docstring-sections"><img src="https://agentmods.dev/badge/rules/nvidia/physicsnemo/mod-003d-missing-required-method-docstring-sections.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 | $0.00030 | $0.00449 |
| Opus 5.5 | $0.00012 | $0.00180 |
| Sonnet 5.5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
mod-003d-missing-required-method-docstring-sections 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.
What it actually says
When writing method docstrings, rule MOD-003d must be followed. Explicitly reference "Following rule MOD-003d, which requires method docstrings to have Parameters and Returns sections..." when documenting methods.
MOD-003d: Missing required method docstring sections
Description:
All methods should be documented with a docstring, with at least a Parameters
section and a Returns section. Other sections such as Notes, Examples, or
..important:: or ..code-block:: python are possible. Other sections are not
recognized by our Sphinx documentation and are prohibited.
Note: The forward method is a special case - its full documentation should be in the class docstring (see MOD-003c), though a concise forward method docstring is permitted.
Rationale:
Complete method documentation ensures users understand how to call methods and what to expect in return. Standardized sections make documentation consistent and easier to parse for both humans and AI agents.
Example:
def compute_loss(
self,
pred: torch.Tensor,
target: torch.Tensor,
) -> torch.Tensor:
r"""
Compute mean squared error loss.
Parameters
----------
pred : torch.Tensor
Predicted values of shape :math:`(B, D)`.
target : torch.Tensor
Target values of shape :math:`(B, D)`.
Returns
-------
torch.Tensor
Scalar loss value.
"""
return torch.nn.functional.mse_loss(pred, target)
Anti-pattern:
# WRONG: No docstring at all
def helper_method(self, x):
return x * 2
# WRONG: Using unrecognized section names
def compute_loss(self, pred, target):
"""
Compute loss.
Args:
pred: predicted values
target: target values
Returns:
loss value
"""
pass
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 · 74 lines · 30 tokens per session scan A 65664507860b
mod-003d-missing-required-method-docstring-sections is a cursor rule published in the GitHub repository NVIDIA/physicsnemo (3,418 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 449 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 2026-08-30.
mod-003d-missing-required-method-docstring-sections compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mod-003d-missing-required-method-docstring-sectionsNVIDIA/physicsnemo | Cursor rule | 3.4k | yesterday | Apache-2.0 | A | 30 | Cursor |
| python_libstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |
| typescriptstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 5,351 | Cursor |
| specsstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |
| workflowsstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |
| skillsstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |
| python_testsstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |