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/1.1.2npx skills add robium-ai/robium --skill 1.1.2git 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/1.1.2)<a href="https://agentmods.dev/skills/robium-ai/robium/1.1.2"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/1.1.2.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 5.1 | $0.00118 | $0.03709 |
| Opus 5 | $0.00059 | $0.01854 |
| Sonnet 5 | $0.00024 | $0.00742 |
| Haiku 4.5 | $0.00012 | $0.00371 |
Grade B, and why
foxglove scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install ros-$ROS_DISTRO-foxglove-bridge How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
foxglove
The remote/web visualization tool for robium: foxglove_bridge exposes a
live ROS 2 graph over a WebSocket, and the Foxglove app (desktop or
app.foxglove.dev in a browser) connects to it or opens a recorded MCAP
file — the answer environments and gazebo route to whenever a robot or
sim runs headless/remote and RViz2's local-display requirement doesn't fit.
Two things changed over time and matter for how this skill is used: the
bridge itself (foxglove_bridge, MIT-licensed, open source) moved its
active development from foxglove/ros-foxglove-bridge (now ROS 1-only,
maintenance mode) to the foxglove/foxglove-sdk monorepo, and the app
that used to be free/open-source "Foxglove Studio" was discontinued in
February 2024 (last open-source release v1.87.0, MPL-2.0) in favor of the
current closed-source, commercial "Foxglove" 2.x app — which does still
ship a free tier the product page states is "free forever" for local/live
visualization, separate from its paid Data Platform/cloud features. The
bridge migration was confirmed via direct fetch of the
foxglove/ros-foxglove-bridge and foxglove/foxglove-sdk GitHub repos this
session; the free-tier claim was confirmed via direct fetch of
foxglove.dev's pricing page, while the Studio-to-2.x licensing history was
reconstructed via search-synthesis after the source blog post 404'd on
direct fetch (see References) — re-verify before repeating either claim,
since licensing terms are exactly the kind of thing that drifts.
When to use this skill
- Setting up
foxglove_bridgeon a robot or sim host, building a layout, recording or replaying an MCAP file, or viewing a robot's data from a machine that isn't the robot itself. - The trigger phrases in the description: 'foxglove', 'mcap', visualizing a robot running on a remote server, sharing visualization with others, recording sessions for later analysis.
- Any time
environmentsorgazebohas already concluded the target is headless/remote and the next question is "how do I actually see it" — this skill is that answer. - Cross-references — go to the sibling skill instead when the question is:
- Whether headless/remote is the deployment target at all, GPU
passthrough, or the general local-vs-remote strategy →
environments(load first if not already decided; this skill assumes that decision is made and just delivers the viz half of it). - Local desktop ROS debugging with a display attached →
rviz2. - ML/data-centric logging outside ROS message types (policy rollouts,
LeRobot episodes) →
rerun— though LeRobot dataset episodes can also be served straight to the Foxglove app vialerobot-dataset-viz --display-mode foxglove(invocation is thelerobotskill's territory; verified 2026-07-12, manip-trial). - Choosing which viz tool fits the situation at all →
visualization(routes here once Foxglove is the right choice).
- Whether headless/remote is the deployment target at all, GPU
passthrough, or the general local-vs-remote strategy →
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 · 257 lines · 118 tokens per session scan B 792aa2310969
foxglove is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 7d ago), licensed MIT. It adds 118 tokens to every session and 3,709 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
telnyx-iot-curl
Manage IoT SIM cards, eSIMs, data plans, and wireless connectivity. Use when building IoT/M2M solutions. This skill provides REST API (curl) examples.
telnyx-networking-curl
Configure private networks, WireGuard VPN gateways, internet gateways, and virtual cross connects. This skill provides REST API (curl) examples.