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-003b-docstring-must-use-raw-string-prefix)<a href="https://agentmods.dev/rules/nvidia/physicsnemo/mod-003b-docstring-must-use-raw-string-prefix"><img src="https://agentmods.dev/badge/rules/nvidia/physicsnemo/mod-003b-docstring-must-use-raw-string-prefix/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-003b-docstring-must-use-raw-string-prefix"><img src="https://agentmods.dev/badge/rules/nvidia/physicsnemo/mod-003b-docstring-must-use-raw-string-prefix.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 | $0.00031 | $0.00338 |
| Opus 5.5 | $0.00012 | $0.00135 |
| Sonnet 5.5 | $0.00006 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
mod-003b-docstring-must-use-raw-string-prefix 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 docstrings, rule MOD-003b must be followed. Explicitly reference "Following rule MOD-003b, which requires docstrings to be prefixed with r"""..." when explaining docstring format.
MOD-003b: Docstring must use raw string prefix r"""
Description:
Each docstring should be prefixed with r""" (not """ or '''). The r
prefix creates a raw string that prevents Python from interpreting backslashes,
which is essential for LaTeX math notation to render correctly in Sphinx
documentation.
Rationale:
LaTeX commands in docstrings use backslashes (e.g., \math, \text). Without
the raw string prefix, Python interprets these as escape sequences, breaking the
documentation rendering.
Example:
class MyModel(Module):
r"""
A model with LaTeX notation.
Parameters
----------
dim : int
Dimension :math:`D` of input features.
"""
pass
Anti-pattern:
# WRONG: Using ''' instead of r"""
class MyModel(Module):
'''
A model with LaTeX notation.
'''
pass
# WRONG: Missing 'r' prefix
class MyModel(Module):
"""
Parameters with shape :math:`(B, D)` # Won't render correctly
"""
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 · 55 lines · 31 tokens per session scan A 432c1fb1b648
mod-003b-docstring-must-use-raw-string-prefix is a cursor rule published in the GitHub repository NVIDIA/physicsnemo (3,418 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 338 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-003b-docstring-must-use-raw-string-prefix compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mod-003b-docstring-must-use-raw-string-prefixNVIDIA/physicsnemo | Cursor rule | 3.4k | yesterday | Apache-2.0 | A | 31 | 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 |
| python_testsstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 0 | Cursor |
| overviewstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 2,612 | Cursor |
| pythonstreamlit/streamlit | Cursor rule | 46k | yesterday | Apache-2.0 | A | 1,192 | Cursor |
| python-stylecpuguy96/StepCOVNet | Cursor rule | 22 | 26d ago | Apache-2.0 | A | 0 | Cursor |