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/skills/dart-verify-sim/SKILL.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/skills/dartsim/dart/dart-verify-sim)<a href="https://agentmods.dev/skills/dartsim/dart/dart-verify-sim"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-verify-sim.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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.
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 | $0.00040 | $0.01755 |
| Opus 5 | $0.00020 | $0.00877 |
| Sonnet 5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
dart-verify-sim 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 4d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DART Simulation Verification
Load this skill when verifying that a DART 3D scene or physics simulation is correct — implementing, debugging, benchmarking, or reviewing dynamics, collision, contact, or GUI output. Modern image-capable agents can inspect a capture, but pixels do not expose solver state and machine image checks are not semantic inspection. This tooling grounds visual reasoning without a GUI.
Lead with text, corroborate with images. Measured A/B evidence: per-step metrics and trajectories detect nearly all seeded physics defects; a rendered image alone misses static geometry defects (penetration, interpenetration). Decide correctness from text; use images for scene comprehension and gross dynamic failures.
Applicability contract
Use this skill for any task whose claim depends on 3D structure or behavior:
model/scene loading, dynamics, collision/contact/constraints, simulation
stepping, GUI/rendering, or visual examples. First run a text oracle (metrics,
scene diff, trajectory/contact comparison, or focused behavioral test), then
corroborate it end to end with an assessed headless view and only the debug
layers needed by the claim. If rendering is unavailable or genuinely
irrelevant, record why and name the replacement evidence; never treat an image
as the sole correctness oracle. When the active agent accepts image input,
actually open and semantically inspect the selected capture; a passing view
report or image-verdict is not visual review.
Full documentation
docs/onboarding/agent-sim-verification.md
— the durable guide. docs/ai/verification.md owns the gate policy;
docs/onboarding/profiling.md owns text-first profiling.
Image-capable review loop
Every lane in the model-routing owner (docs/ai/README.md § "Model
Routing") is image-capable and supports native image input and
original-detail inspection; a model-upgrade audit re-verifies that property
and updates the owner, not this skill. Keep this loop capability-based.
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.
- 4d ago Changed · -1 lines 5e3cfc32cade
- 6d ago First seen · 137 lines · 40 tokens per session scan A 55d4deb0d3b4
dart-verify-sim is a skill published in the GitHub repository dartsim/dart (1,202 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 40 tokens to every session and 1,755 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.
Other skills, from other repositories
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…
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…
sprite-gen
Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…
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.