Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nebius/nebius-physical-ainpx agentmods add skills/nebius/nebius-physical-ai/artifact-viz-shareWrote 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/nebius/nebius-physical-ai/artifact-viz-share)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/artifact-viz-share"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/artifact-viz-share/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/artifact-viz-share"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/artifact-viz-share.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01816 |
| Opus 5 | $0.00041 | $0.00908 |
| Sonnet 5 | $0.00016 | $0.00363 |
| Haiku 4.5 | $0.00008 | $0.00182 |
Grade A, and why
artifact-viz-share 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 4d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact conversion, visualization, and sharing
Three small command groups cover the last mile between a finished run and a
human looking at it. They are standalone and local-first: none of them needs a
cluster, and all of them accept s3:// on both sides.
Pick by what you have and what you need:
| Have | Want | Command |
|---|---|---|
| Genesis/sim episode numpy arrays | A trainable dataset | npa adapter convert |
| LeRobotDataset | Interactive timeline | npa convert lerobot-to-rrd |
| LeRobotDataset | A video to paste in a review | npa convert lerobot-to-mp4 |
.rrd recording |
A link someone else can open | npa rerun host / share |
Sim output → LeRobotDataset
npa adapter convert \
--input-path ./data/demos/ \
--output-path ./data/lerobot_dataset/ \
--fps 20 --robot franka_panda \
--task "Pick and place cube to target"
Converts Genesis/sim demo numpy arrays to LeRobotDataset v3. This is the seam
between simulation and policy training: --fps is the video encoding rate, and
--task becomes the dataset's task description, so set it to what the episodes
actually show rather than leaving the default. -i/-o are accepted aliases.
LeRobotDataset → Rerun recording
npa convert lerobot-to-rrd \
--input-path s3://<bucket>/datasets/<name>/ \
--output-path s3://<bucket>/reports/<name>.rrd \
--duration 30 \
--predictions-path s3://<bucket>/eval/groot-predictions.json
.rrd is the interactive format — scrub the timeline, inspect per-frame state.
--predictions-path overlays a GR00T prediction artifact on the ground-truth
trajectory, which is how you see where a policy diverges rather than only that
it scored badly. --duration caps the recording; the default is the adapter cap.
The SDK entrypoint is npa.convert.lerobot_to_rrd(input_path=..., output_path=..., predictions_path=...). Pass an S3 destination as a string:
the SDK uploads the recording and returns the unchanged URI. Local destinations
return a Path. Constructing Path("s3://...") removes a slash and changes the
destination into a local path. Verify uploaded bytes and decode the recording
before treating its returned reference as an artifact handoff.
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.
- 4d ago Changed · +7 lines 48370a8c3066
- 6d ago Changed · +21 lines 9945d9be52aa
- 12d ago First seen · 127 lines · 82 tokens per session scan A b3319f004dc4
artifact-viz-share is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,816 once invoked, about $0.0004 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
stable-diffusion
Text-to-image generation, inpainting, and img2img.
huggingface-lora-space-builder
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers…
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.