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 skills/robium-ai/robium/1.3.2npx skills add robium-ai/robium --skill 1.3.2git clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/1.3.2)<a href="https://agentmods.dev/skills/robium-ai/robium/1.3.2"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/1.3.2.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 | $0.00147 | $0.05329 |
| Opus 5 | $0.00073 | $0.02665 |
| Sonnet 5 | $0.00029 | $0.01066 |
| Haiku 4.5 | $0.00015 | $0.00533 |
Grade B, and why
gazebo scanned grade B with 2 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install ros-jazzy-ros-gz Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
and **Harmonic** (LTS, Sep 2023 – May 2029) — verified by direct `curl` of Copies of this mod
1 near-identical copy found in the catalogue:
- gazebo — 100% identical, 103 lines differ
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gazebo
The sim half of the robium nav-vertical trial run: modern Gazebo (the gz
tools — Gazebo Classic/gazebo11 is a separate, EOL project and out of scope
everywhere in this skill) for building SDF worlds and models, attaching
sensors, bridging topics to ROS 2 via ros_gz, spawning robots, and running
headless. as of 2026-07-10, Gazebo's current named releases are Jetty
(LTS, Sep 2025 – May 2031), Ionic (standard support, Sep 2024 – Dec 2026),
and Harmonic (LTS, Sep 2023 – May 2029) — verified by direct curl of
gazebosim.org/docs/all/releases/ on 2026-07-10, which also lists the older
Fortress LTS (Sep 2021 – May 2027) still inside its support window. Jetty is
now the newest LTS, one release past the Harmonic/Ionic line named in this
skill's description; re-verify the release list before trusting any of this
paragraph in a future session; see references/worlds-and-models.md's
sourcing note. The robium nav vertical (nav2 skill) targets ROS 2 Jazzy
Jalisco, whose paired Gazebo release is Harmonic — the ros_gz
jazzy branch ships prebuilt binaries for that pairing from
packages.ros.org, confirmed by direct fetch of the ros_gz README this
session (see References). This skill's nav-facing snippets and examples
target Jazzy + Harmonic for that reason; Ionic (paired with Kilted) is
nearing its Dec 2026 EOL, and Jetty (the newest LTS) pairs with Lyrical or
Rolling, not Jazzy — don't pick either for a new Jazzy-based project without
re-checking the table first.
When to use this skill
- Building or editing an SDF world or model, adding a sensor (lidar, camera,
IMU, contact) to a robot, wiring a
ros_gzbridge, spawning a robot into a running simulation, or running Gazebo headless/server-only. - The trigger phrases in the description: 'gazebo', 'gz sim', 'ros_gz', 'simulate the robot', 'add a lidar to the sim'.
- Someone mentions Gazebo Classic tutorials,
gazebo11, or the oldlibgazebo_ros_*plugin names — flag that they don't apply here (Classic is EOL) and redirect to this skill's moderngz/ros_gzequivalents. - Cross-references — go to the sibling skill instead when the question is:
- Which simulator to use at all (Gazebo vs. Isaac Sim vs. something
else) → the
simulationskill. This skill assumes Gazebo has already been chosen. - Generic ROS 2 mechanics the bridge or a spawned robot's launch file rides
on (workspaces, colcon, launch files, TF2 concepts, QoS) →
ros2. This skill's only TF content is what theros_gzbridge or a sim plugin itself publishes. - Navigation behavior once sensor data is flowing (costmaps, AMCL,
behavior trees) →
nav2. This skill stops at "sensor topics are bridged and correctly framed"; what Nav2 does with them isnav2's territory. - Isaac Sim specifically →
isaac-sim. - Running
gz/ros_gzinside Docker, GPU passthrough for the container, or macOS/remote-server environment strategy →environments. This skill's Platform gotchas section only notes where Docker changes gz's own behavior (rendering, display), not how to set the container up. - The whole-stack decision this feeds into →
architect(routes here).
- Which simulator to use at all (Gazebo vs. Isaac Sim vs. something
else) → the
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 322 lines · 147 tokens per session scan B 885a3bf019e4
gazebo is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 7d ago), licensed MIT. It adds 147 tokens to every session and 5,329 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aerospace-engineering-technician
Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…
automotive-engineering-technician
Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…
biomass-plant-technician
Use when a task needs the judgment of a Biomass Plant Technician — adjusting combustion parameters in response to actual measured fuel moisture content rather than a fixed setpoint, diagnosing a fuel feed interruption as mechanical bridging rather than a combustion issue, adjusting soot-blowing frequency to actual…
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.