dart: Skill for Claude Code

.agents/skills/dart-architecture/SKILL.md

dart-architecture is a skill for Claude Code, Codex from dartsim/dart. It costs 41 tokens per session (2,493 once invoked), scanned A, original, BSD-2-Clause.

An architectural guide to DART 7, a simulation system for multiple kinds of physics, solvers, and computing backends.

In plain words
What is it for?
Use it to understand DART’s world, physics domains, solvers, couplers, compute graphs, and execution backends.
Why use it?
It explains where major responsibilities belong, helping developers extend the simulation without bypassing its shared abstractions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

This is dartsim/dart's own configuration. It tells Claude Code and Codex how to work on dart itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dart configures →

About the project

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.

dartsim/dart · 1,204 stars · on GitHub · dart.readthedocs.io

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/dartsim/dart/main/.agents/skills/dart-architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dartsim/dart

Made for: Claude Code, Codex.

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.

agentmods badge for dart-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/dartsim/dart/dart-architecture/github.svg)](https://agentmods.dev/skills/dartsim/dart/dart-architecture)
Your own site
<a href="https://agentmods.dev/skills/dartsim/dart/dart-architecture"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-architecture/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.

agentmods 80×15 button for dart-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/dartsim/dart/dart-architecture"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 10 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 7
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Prompt Injection · line 45
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 47
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 49
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 50
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 51
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 148
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 151
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 152
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 154
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.02493
Opus 5 $0.00020 $0.01247
Sonnet 5 $0.00008 $0.00499
Haiku 4.5 $0.00004 $0.00249

Measured 2d ago against content hash 6cddfdc47d91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dart-architecture 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.

.agents/skills/dart-architecture/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DART 7 Architecture

Load this skill when working on the DART 7 simulation World, on solvers/physics domains/compute backends, when a change adds or renames a dart/simulation module, step-stage slot, or solver family, or whenever a task needs the big-picture map of how DART 7 is generalized for multi-physics, multi-solver, and multi-backend simulation.

The design in one sentence

World owns topology, time and composition. A solver may advance one or several physical domains, using a shared solve or an explicit coupling strategy. Semantic dependencies, executable plans and runtime adapters separate physics from scheduling. Users configure DART-owned method/policy values, never solver registries, component storage or runtime objects.

Why three axes of choice

  • Research, apples-to-apples. A new paper's algorithm should be reproducible and benchmarkable inside DART against baselines on shared foundations, not in a fork. New methods enter through DART-owned solver families.
  • End-user choice. Users pick the solver method and (internally) backend that fit their accuracy/speed/platform needs.
  • Auto-configuration. Defaults are selected from scene content so the easy path stays trivial; the backend seam is designed for later platform/scene-scale awareness without changing the public API.

The living architecture map

The published page docs/readthedocs/architecture.md embeds four views that are rendered at docs-build time from typed JSON under docs/assets/architecture/. The JSON is the source of truth; rendered HTML is never committed.

View Owns
simulation-framework.architecture.json facade → scene → selection → schedule → solver families → data/collision → compute; every dart/simulation/<dir> except compute/
world-step.dataflow.json the built-in World::step() stage slots as nodes (ids are BuiltInWorldStepStageSlot names in snake case) plus the two listed bookends sync and continuation for the prologue and epilogue outside the schedule, flows named by exchanged data
compute-graph.architecture.json semantic graph → executable plan → runtime adapters → evidence; dart/simulation/compute/**
library-context.architecture.json every dart/<module>, dartpy, dartsim, external dependencies
compute-graph.runtime.json fixture recorded by tests/unit/simulation/compute/test_architecture_probe.cpp for the advisory runtime drift check

Read the full file on GitHub · 182 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.

  1. 2d ago Changed · +94 lines · +9 tokens per session 6cddfdc47d91
  2. 8d ago First seen · 88 lines · 32 tokens per session scan A 0d6cf7fe30e0

Subscribe to this mod's changes

dart-architecture is a skill published in the GitHub repository dartsim/dart (1,204 stars, last pushed 2d ago), licensed BSD-2-Clause. It adds 41 tokens to every session and 2,493 once invoked, about $0.0002 per session on Opus 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 2026-09-01.

Related

Other skills, from other repositories

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

agent-based-social

Use this Skill for agent-based social modeling with Mesa: opinion dynamics, segregation, social contagion, and network diffusion simulations.

xjtulyc/awesome-rosetta-skills · 29 tokens

sdf

SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for .sdf files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh URIs, sensors, lights, physics, plugins, includes, Gazebo, static SDF review, or simulator-specific metadata. Do not use…

earthtojake/text-to-cad · 88 tokens

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…

earthtojake/text-to-cad · 111 tokens

fine-tuning-serving-openpi

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging…

Orchestra-Research/AI-Research-SKILLs · 87 tokens

fine-tuning-openvla-oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying…

Orchestra-Research/AI-Research-SKILLs · 103 tokens