What is newton-cli CLAUDE.md?

Project instructions for newton-cli, a command-line program that lets an AI agent control NVIDIA’s Newton physics engine without writing Python. The repository uses real Newton examples as its specification.

Use it when building or changing newton-cli, arranging its standard source layout, and adding commands needed to reproduce upstream Newton examples and pass their checks.

It gives contributors a shared way to decide what the CLI should support and how to test it. This keeps development tied to working examples instead of an assumed complete API.

How Terry-cyx/newton-cli configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Terry-cyx/newton-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Terry-cyx/newton-cli/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Terry-cyx/newton-cli

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/terry-cyx/newton-cli/claude-md/github.svg)](https://agentmods.dev/instructions/terry-cyx/newton-cli/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/terry-cyx/newton-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/terry-cyx/newton-cli/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/terry-cyx/newton-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/terry-cyx/newton-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,859 This file is loaded in full into every session.

When invoked 1,859 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01859	$0.01859
Opus 5.5	$0.00744	$0.00744
Sonnet 5.5	$0.00372	$0.00372
Haiku 4.5	$0.00186	$0.00186

Measured 2mo ago against content hash 6e2115ec6a4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

newton-cli CLAUDE.md 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.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project goal

Build newton-cli — an agent-native CLI wrapper around NVIDIA's Newton physics engine — so an LLM agent can drive Newton without writing Python.

Defining principle: Newton's examples/ directory is the spec. The CLI is "complete" when every example under ../newton/newton/examples/ can be reproduced by a sequence of newton-cli invocations that pass the example's own test_final() validation. We do not enumerate Newton's API surface top-down; we grow the CLI bottom-up from real example demand. If a CLI command isn't needed to run an example, it doesn't get built (yet).

Repository layout (standard src layout)

This project lives at E:/newton-cli/newton_cli/. The vendored Newton source is a sibling at E:/newton-cli/newton/. The two-folder split keeps upstream untouched.

E:/newton-cli/
├── newton/                     # vendored upstream Newton (read-only)
└── newton_cli/                 # THIS project
    ├── .venv/                  # local virtualenv (uv)
    ├── pyproject.toml          # depends on newton via path "../newton"
    ├── README.md
    ├── CLAUDE.md               # this file
    ├── PLAN.md                 # wave-by-wave execution plan
    ├── src/
    │   └── newton_cli/         # the Python package
    │       ├── __init__.py
    │       ├── __main__.py     # lazy-inits Warp under stdout redirect
    │       ├── cli.py          # argparse dispatcher
    │       ├── io.py           # emit / fail envelope helpers
    │       ├── _introspect.py  # allow-list API walker
    │       ├── _warp.py        # silent Warp init
    │       ├── recipes.py      # JSON recipe → ModelBuilder
    │       ├── sim.py          # step loop
    │       └── state_io.py     # .npz round-trip
    ├── tests/
    │   ├── _cli.py             # subprocess runner helper
    │   ├── test_phase0_introspection.py
    │   └── test_examples/      # one test file per Newton example
    ├── logs/                   # wave logs + session summaries
    └── prompts/                # prompt fragments (bootstrap etc.)

Read the full file on GitHub · 111 lines

Changes

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 · 111 lines · 1,859 tokens per session scan A 6e2115ec6a4c

Subscribe to this mod's changes

newton-cli CLAUDE.md is an instructions file published in the GitHub repository Terry-cyx/newton-cli (4 stars, last pushed 7mo ago), licensed MIT. It adds 1,859 tokens to every session, about $0.0074 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.

Game development

newton-cli CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
newton-cli CLAUDE.mdTerry-cyx/newton-cli	Instructions file	4	7mo ago	MIT	A	1,859	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

newton-cli: Instructions file for Claude Code