Skip to content
Back to skills

Dimos

ASecurity

Create and inspect robotics projects in the DimOS Harness workspace, including its local starter and optional upstream integration.

  • 1,124 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agentsapi

Works with

  • api

Security analysis

A100/100

Scanned September 19, 2026

npx -y skills add autonomous-ai/openharness --skill dimos --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dimos?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Dimos
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/autonomous-ai-dimos/badge)](https://www.skillsdirectory.com/skills/autonomous-ai-dimos)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: dimos
description: Create and inspect robotics projects in the DimOS Harness workspace, including its local starter and optional upstream integration.
---

# Mission control

Read `studio.json` to understand the current controls; `"$STUDIO_TOOLCHAIN/../studio.config.json"`
describes their ranges. Run `"$STUDIO_TOOLCHAIN/run.sh" simulate` to make a new result.
Successful artifacts and their measurements are in `out/runs/<id>/`; `out/latest.json` names the
current result. A failed run preserves the last success and records the error in the verdict.

The starter performs A* route planning and real MuJoCo dynamics in an original two-dimensional office rover model. It is not a Unitree robot or physical execution. DimOS is fetched at a pinned source commit; its full daemon and perception stack are an optional, larger installation.

Use `"$STUDIO_TOOLCHAIN/../README.md"` for the integration contract and commands. Read the relevant
files under `$STUDIO_UPSTREAM` before using an upstream API. Keep controls within their documented
ranges, preserve the data needed to reproduce a comparison, and distinguish preview results from
native service or hardware output. The viewer supports history and artifact downloads; tell the
user which run contains the result, and what was actually measured.

## Plan, execute, inspect

Choose an open destination in the office or gallery. Run `simulate`, then inspect
`mission.json` and `mission.xml`. Check arrival, final position, travel time, distance, and wall
contacts. Replay uses the recorded MuJoCo positions. A destination inside the inflated
obstacle boundary must fail explicitly; choose another destination instead of inventing a path.

Read `$STUDIO_UPSTREAM/docs/quickstart.md` and `docs/installation/osx.md` before working with
DimOS itself. The local starter is an original planar rover, not a Unitree simulation. The
optional `dimos` action only reads daemon status. Simulation success never implies a physical
robot reached its destination.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…