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-model-upgrade/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-model-upgrade)<a href="https://agentmods.dev/skills/dartsim/dart/dart-model-upgrade"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-model-upgrade/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/skills/dartsim/dart/dart-model-upgrade"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-model-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.02280 |
| Opus 5 | $0.00023 | $0.01140 |
| Sonnet 5 | $0.00009 | $0.00456 |
| Haiku 4.5 | $0.00005 | $0.00228 |
Grade A, and why
dart-model-upgrade 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dart-model-upgrade
Use this skill in Codex to run the DART dart-model-upgrade workflow. The editable
workflow source lives in .claude/commands/; this file is its generated adapter
in the shared .agents/skills/ catalog.
Invocation
- Claude Code:
/dart-model-upgrade <arguments> - Codex:
$dart-model-upgrade <arguments>
Treat the text after the skill name as $ARGUMENTS. When the workflow
references $1, $2, etc., map those to the positional values supplied by the
user.
Command Body
Improve DART's AI harness for: $ARGUMENTS
Objective
A named model triggers a whole-harness audit: skills, instructions, docs,
context/state ownership, tools, agents, hooks, and verification, including this
workflow — review both content and structure using the audit contract in
docs/ai/components.md; updating a model-routing entry is not the whole task.
Later model/effort preferences constrain execution, not this coverage, unless
the user explicitly narrows the audit. Prefer coherent evidence-backed changes:
substantial restructuring is welcome when comparisons show a benefit, while
more machinery or fewer words alone do not establish improvement.
Required Reading
Read the compact intake first: @AGENTS.md @docs/ai/principles.md @docs/ai/components.md
Then load the relevant sections at the phase that needs them; audit each surface without loading every referenced document in full:
- Target/control:
docs/ai/README.md§ "Model Routing" and the target tool's section indocs/onboarding/ai-tools.md. - Structure/discovery: relevant rows of
docs/ai/workflows.md, the docs map and placement matrix indocs/README.md, anddocs/AGENTS.mdbefore documentation changes. - Project state: current state in
docs/ai/north-star.md,docs/plans/dashboard.md, and one representative active plan/handoff;docs/dev_tasks/README.mdanddocs/ai/orchestration.mdown continuation and phase-specific authorization. Search long handoffs for current state before reading history. - Comparison/gates:
docs/ai/verification.mdanddocs/onboarding/agent-sim-verification.mdwithdart-verify-sim. - Tracking/closeout:
docs/dev_tasks/README.md; load changelog policy only at closeout. Usedocs/plans/README.mdonly when changing plan state.
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 · +1 lines d34189d4178a
- 4d ago Changed · -47 lines · +3 tokens per session 0dca1c1afd09
- 6d ago Changed · +6 lines d68742db3c7d
- 8d ago First seen · 211 lines · 42 tokens per session scan A be9d7ffc072d
dart-model-upgrade is a skill published in the GitHub repository dartsim/dart (1,204 stars, last pushed 3d ago), licensed BSD-2-Clause. It adds 45 tokens to every session and 2,280 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
mjlab-to-mjswan
Port an mjlab task to mjswan: turn a local or remote GitHub repo that registers mjlab tasks into a browser app. Use when the user wants to run, visualize, or deploy an mjlab task (theirs or a third party's) in the browser with mjswan.
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…
pufferlib
Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.
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.
ai-game-world-design
Complete mastery guide for designing and building AI-powered game worlds — procedural world generation, NPC behavior trees, LLM-driven dialogue systems, emergent storytelling, economy simulation, player modeling, and real-time difficulty adaptation. Covers the full stack from world-building fundamentals to integrating…
authoring-pipelines
Use when the user wants a bagel data pipeline — reducing a log to windows around events ("keep 30s around every hard brake"), recurring snippets/GIFs/exports, or any tasks-and-gates automation over robot data.