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/kornia/bubbaloop/openclawnpx skills add kornia/bubbaloop --skill openclawgit clone --depth 1 https://github.com/kornia/bubbaloopWhat 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 | $0.00040 | $0.00652 |
| Opus 5 | $0.00020 | $0.00326 |
| Sonnet 5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
bubbaloop-physical-ai 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 2d 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.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bubbaloop Physical AI Skill
You have access to a physical sensor network managed by bubbaloop. Use the bubbaloop MCP tools to interact with hardware.
Quick Reference
Discover what's available
list_nodes— See all registered sensor/actuator nodes and their statusget_node_detail(name)— Get detailed info about a specific nodeget_system_status— Overview of the entire system
Read sensor data
query_zenoh(key_expression)— Query any Zenoh topic for current data- Use
bubbaloop/**/outputto find all sensor outputs - Use
bubbaloop/**/health/*to check node health - Use
bubbaloop/**/manifestto discover node capabilities
- Use
Control nodes
start_node(name)— Start a stopped nodestop_node(name)— Stop a running noderestart_node(name)— Restart a nodeinstall_node(name)— Install a node as a system servicebuild_node(name)— Build a node from source
Monitor
get_node_health(name)— Check if a node is healthyget_node_logs(name)— View recent logsget_stream_info(name)— Get Zenoh connection params for streaming data
Configure
get_node_config(name)— Read node configurationsend_command(name, command, params)— Send commands to nodes
Common Patterns
"What sensors are available?"
Call list_nodes to see all nodes. Each node's status shows if it's Running, Stopped, or Failed.
"What's the temperature?"
- Call
list_nodesto find temperature-related nodes - Call
query_zenoh("bubbaloop/**/output")to read current values - Parse the protobuf or JSON response
"Start monitoring cameras"
start_node("rtsp-camera")to ensure the camera node is runningget_stream_info("rtsp-camera")to get the Zenoh topic for live frames
"Something seems wrong"
get_system_statusfor overviewget_node_health(name)for specific node healthget_node_logs(name)for recent logs
Architecture
bubbaloop uses a dual-plane model:
- MCP (Control Plane): You interact here — lifecycle, config, commands
- Zenoh (Data Plane): Real-time sensor data flows here — pub/sub, queryables
What ships with it
2 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.
- 2d ago First seen · 70 lines · 40 tokens per session scan A 41c4ff5b6547
bubbaloop-physical-ai is a skill published in the GitHub repository kornia/bubbaloop (28 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 652 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
habitat-gs-control
Interactively pilot a robot in habitat-gs 3D Gaussian Splatting indoor scenes via MCP tools — load a scene, move, observe with RGB/depth, run autonomous nav loops, and export video. Use for hands-on control of a live sim session, NOT for training or evaluating a navigation policy (use the habitat-gs-train skill for…
vss-generate-video-calibration
Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.
voyager-launch
Complete one-shot Voyager SDK launcher for Axelera AI Metis pipelines and demos. Use when the user asks to build, create, launch, run, verify, package, open a browser result viewer, or show results for a complete AI vision pipeline from a natural-language request (including when they want to debug or evaluate a…
voyager-debug
Systematically debug and fix issues with Axelera AI Voyager SDK pipelines, models, inference, installation, or hardware. Use when the user brings an existing error, log, crash, accuracy issue, or regression, or when the Voyager SDK install is missing, broken, or outdated, the driver or firmware mismatch, or the Metis…
voyager-new-app
Create or modify a standalone Python application using the Voyager SDK InferenceStream/createinferencestream API for Axelera AI Metis hardware. Use when the user explicitly asks for app code, monitoring, analytics, REST API, custom UI, multi-stream logic, alerts, or business logic around an existing/validated…
voyager-bench
Benchmark model performance on Axelera AI Metis hardware with the Voyager SDK. Use when the user wants to measure FPS, throughput, latency, or compare model variants. Use to quantify a working pipeline. Prefer voyager-debug when performance is a suspected fault or regression.