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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/dartsim/dart/dart-new-taskgit 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/commands/dartsim/dart/dart-new-task)<a href="https://agentmods.dev/commands/dartsim/dart/dart-new-task"><img src="https://agentmods.dev/badge/commands/dartsim/dart/dart-new-task.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00845 |
| Opus 5 | $0.00009 | $0.00423 |
| Sonnet 5 | $0.00003 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
dart-new-task 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 yesterday.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a new task in DART: $ARGUMENTS
Required Reading
Read these files first: @AGENTS.md @docs/onboarding/building.md @docs/onboarding/contributing.md @docs/onboarding/code-style.md @docs/dev_tasks/README.md @docs/information-architecture.md @docs/ai/sessions.md @docs/ai/principles.md @docs/ai/verification.md
Workflow
- Understand the task - Parse: goal, constraints, type (feature|bugfix|refactor|docs)
- Assess scope - Multi-phase or multi-session? Create
docs/dev_tasks/<task>/(seedocs/dev_tasks/README.mdfor criteria). Team-scale work (multiple parallel lanes needing orchestrated worker agents) switches todart-ultraworkinstead. For multi-session, design-heavy, public API, solver/paper, release, or cross-module work, fill the dev-task specification intake before editing: value, scope, assumptions, traceability, non-goals, acceptance evidence, gates, and open decisions. If consequential ambiguity would change public API, release compatibility, numerical correctness, benchmark claims, or roadmap scope, record an owner-localDecision neededblock instead of silently choosing. - Setup - Choose the target branch before creating a topic branch:
- features/docs/non-bugfix refactors: branch from
origin/main - bug fixes that apply to the current release line: branch from the active
DART 6 LTS
origin/release-6.*branch first, then cherry-pick or reapply tomain
- features/docs/non-bugfix refactors: branch from
- Implement - Keep commits focused, follow code style
- Verify - Run
pixi run lintbefore committing, then the gate set for this task type fromdocs/ai/verification.md. If the claim depends on 3D structure or behavior, route throughdart-verify-sim: text oracle first, then assessed claim-tied visual evidence, or record why it is not applicable. - PR - After explicit maintainer/user approval,
git push -u origin HEADthengh pr create --draft --base <target-branch> --milestone "<milestone>"(DART 7.0formain, branch-matching DART 6.x release milestone for the active DART 6 LTS branch); follow.github/PULL_REQUEST_TEMPLATE.md - Cleanup - Before PR: if task used
docs/dev_tasks/<task>/, first promote durable dashboards, evidence matrices, API inventories, migration maps, or long-lived decisions into the durable owner selected bydocs/information-architecture.md. Then remove the dev-task folder completely (include the deletion in this PR, not after merge).
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.
- yesterday Changed · -14 lines c80807e55850
- 3d ago First seen · 87 lines · 17 tokens per session scan A becb15d0b2a6
dart-new-task is a command published in the GitHub repository dartsim/dart (1,201 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 17 tokens to every session and 845 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.
Other commands, from other repositories
mission
List active missions with their constraints and alerts.
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.