DART is an open-source C++23 physics engine that simulates the movement and interactions of articulated rigid-body systems for robotics, animation, and machine learning. Researchers and developers use it for kinematics, dynamics, collision handling, constraints, and loading robot models, with C++ and Python interfaces. The catalogue add-ons support workflows built around this engine.
Borrowing it
Nothing to install: this file belongs to dartsim/dart. 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/dartsim/dart/main/AGENTS.mdgit clone --depth 1 https://github.com/dartsim/dartWrote 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/instructions/dartsim/dart/agents-md)<a href="https://agentmods.dev/instructions/dartsim/dart/agents-md"><img src="https://agentmods.dev/badge/instructions/dartsim/dart/agents-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.
<a href="https://agentmods.dev/instructions/dartsim/dart/agents-md"><img src="https://agentmods.dev/badge/instructions/dartsim/dart/agents-md.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 | $0.01799 | $0.01799 |
| Opus 5.5 | $0.00720 | $0.00720 |
| Sonnet 5.5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
dart AGENTS.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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for DART
This file is the single shared rules file and repository pointer board for
Claude Code, Codex, and Muse; keep shared guidance here (see
docs/onboarding/ai-tools.md). Start every task with
docs/ai/principles.md, then load only the owner docs needed for the work.
Delegate by default under docs/ai/orchestration.md; honor a per-task
delegation=off opt-out.
@docs/ai/principles.md
Project Profile
- WHAT: C++17 robotics physics engine with dartpy bindings (nanobind)
- WHY: A Python-first DART 7 that stays compatible with Gazebo/gz-physics
- HOW: Use repository
pixi run ...tasks; runpixi run lintbefore commits
Quick Commands
pixi run config # Configure the default CMake/Ninja build
pixi run build # Build C++ libraries and utilities
pixi run test # Build and run C++ tests
pixi run build-py-dev # Build dartpy
pixi run test-py # Run dartpy tests
pixi run test-all # Build defaults and run C++/Python tests
pixi run test-gui # Run Filament GUI tests that need a graphics device
pixi run lint # Format C++, CMake, Python, TOML; fix spelling (auto-fixes)
pixi run check-lint # Run the non-mutating lint aggregate
For downstream-sensitive changes, also run pixi run -e gazebo test-gz.
See docs/onboarding/ci-cd.md when a gate fails.
Task-specific Context
| Task | Load these owners |
|---|---|
| Any task | docs/ai/principles.md |
| Architecture or component boundaries | docs/onboarding/architecture.md |
| Building or dependencies | docs/onboarding/building.md, docs/onboarding/build-system.md |
| Testing or simulation evidence | docs/onboarding/testing.md, docs/ai/verification.md; use dart-verify-sim |
| Performance investigations or claims | docs/onboarding/profiling.md § "Performance Methodology"; use dart-perf |
| Contribution, branches, or style | docs/onboarding/contributing.md, docs/onboarding/code-style.md, CONTRIBUTING.md |
| Documentation placement | docs/README.md, docs/information-architecture.md, docs/AGENTS.md |
| AI workflows or tooling | docs/ai/README.md, docs/ai/workflows.md, docs/ai/terminology.md, docs/onboarding/ai-tools.md |
| Planning or autonomous work | docs/ai/north-star.md, docs/plans/dashboard.md, docs/ai/orchestration.md, docs/ai/sessions.md |
| CI failures | docs/onboarding/ci-cd.md |
| Python bindings | docs/onboarding/python-bindings.md |
| Model loading and parsers | docs/onboarding/io-parsing.md |
| Release maintenance | docs/onboarding/release-management.md |
| Changelog decisions | docs/onboarding/changelog.md, docs/onboarding/release-management.md |
| Multi-session dev tasks | docs/dev_tasks/README.md |
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.
- 2d ago Changed · +2 lines · +8 tokens per session 313629ce925d
- 5d ago Changed · +1 lines · +19 tokens per session edd836f913e1
- 6d ago Changed · +2 lines · +41 tokens per session aa575e42c933
- 10d ago Changed · +2 lines · +27 tokens per session b2efc6e3dd1e
- 14d ago Changed · +13 lines · +144 tokens per session e5229fbab52b
- 16d ago Changed · +7 lines · +141 tokens per session 9c27d0776698
- 17d ago Changed · +5 lines · +25 tokens per session 87cc096d255b
- 19d ago Changed · +1 lines · +28 tokens per session 94cbb747fd3d
- 20d ago Changed · +3 lines · +48 tokens per session d979696241fb
- 22d ago First seen · 99 lines · 1,318 tokens per session scan A 0aa1622b7eac
dart AGENTS.md is an instructions file published in the GitHub repository dartsim/dart (1,220 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 1,799 tokens to every session, about $0.0072 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 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.