dart: Skill for Claude Code

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

dart-pr is a skill for Claude Code from dartsim/dart. It costs 22 tokens per session (1,213 once invoked), scanned A, original, BSD-2-Clause.

A workflow for preparing a DART pull request by creating a branch, committing changes, pushing them, and opening the request.

In plain words
What is it for?
Reading contribution guidance, checking recent pull-request patterns, drafting the request, and publishing it after approval.
Why use it?
It provides a consistent path from local code changes to a reviewable pull request and includes the project's required documentation.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

This is dartsim/dart's own configuration. It tells Claude Code 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 · 1,202 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-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dartsim/dart

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.

agentmods badge for dart-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/dartsim/dart/dart-pr.svg)](https://agentmods.dev/skills/dartsim/dart/dart-pr)
Your own site
<a href="https://agentmods.dev/skills/dartsim/dart/dart-pr"><img src="https://agentmods.dev/badge/skills/dartsim/dart/dart-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 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 pass 7 Sept 2026
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 $0.00022 $0.01213
Opus 5 $0.00011 $0.00607
Sonnet 5 $0.00004 $0.00243
Haiku 4.5 $0.00002 $0.00121

Measured today against content hash c949530ed8fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dart-pr 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 today.

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-pr/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dart-pr

Use this skill in Codex to run the DART dart-pr 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-pr <arguments>
  • Codex: $dart-pr <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

Prepare the PR locally within the authorized task: $ARGUMENTS Before an action requiring explicit maintainer/user approval under the owner docs, verify that existing authorization covers its action, target, and scope. Ask only for missing or changed authority after completing authorized preparation.

Required Reading

@AGENTS.md @docs/onboarding/contributing.md @docs/onboarding/ai-reviews.md @docs/ai/verification.md @docs/onboarding/changelog.md @.github/PULL_REQUEST_TEMPLATE.md

Drafting the PR

Follow the PR-writing guidance in docs/onboarding/contributing.md#submitting-a-pull-request and fill the compact PR template. Keep titles plain, scoped, and outcome-focused, without agent prefixes. Recent PRs can supply relevant context; use the current owner guidance rather than copying their length or structure.

Draft from the final diff and the reason for it, not from the session report. Before publication, read the rendered body as a reviewer: the opening must explain the concrete problem and solution, and the rest must earn its space through review-relevant rationale or evidence. Short but generic is not enough.

For 3D structure or behavior changes (model/scene, dynamics, collision/contact, simulation, rendering, GUI, visual examples), use dart-verify-sim. Preserve the owner's visible media, assessed comparisons, text oracle, claim boundaries, and reproduction evidence. Publish transient evidence with pixi run evidence-publish as described in docs/onboarding/agent-sim-verification.md; never commit transient evidence. A compact template does not reduce these requirements.

Read the full file on GitHub · 123 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. today Changed · -14 lines c949530ed8fa
  2. 4d ago Changed · -17 lines 1bdd7b561cf7
  3. 6d ago First seen · 154 lines · 22 tokens per session scan A 0ea55b614c60

Subscribe to this mod's changes

dart-pr is a skill published in the GitHub repository dartsim/dart (1,202 stars, last pushed today), licensed BSD-2-Clause. It adds 22 tokens to every session and 1,213 once invoked, about $0.0001 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.