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 skills add nebius/nebius-physical-ai --skill embodiedgengit clone --depth 1 https://github.com/nebius/nebius-physical-aiWrote 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/embodiedgen)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/embodiedgen"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/embodiedgen/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/embodiedgen"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/embodiedgen.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.01294 |
| Opus 5.5 | $0.00017 | $0.00518 |
| Sonnet 5.5 | $0.00008 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
embodiedgen 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 10d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EmbodiedGen V2 image-to-rigid-object
Use this skill only for the scoped, Tier-1 EmbodiedGen V2 workflow. The stable
user surface is workflows/testing/byof-embodiedgen.yaml
through generic npa workbench workflow commands—not a persistent service,
separate SDK submitter, or an embodiedgen command family. Start with the
operator guide, then use the
workflow catalog
and OSS capability record.
Capability boundary
The qualified private capability is
img3d-cli_trellis_image_to_urdf_pybullet. The real upstream TRELLIS backend
runs through EmbodiedGen img3d-cli, emits a URDF and collision meshes,
converts that URDF to MJCF, and validates the exact generated URDF in PyBullet
for gravity contact, settling, and a fully decoded MP4. TRELLIS is selected;
SAM3D and the Tencent cloud backend are not substitutes.
Generated mass, height, and friction are VLM estimates—not calibrated ground truth. Do not claim articulated-object generation, physics validation in MuJoCo/Genesis, downstream policy improvement, or model quality. MJCF is a supported handoff only; PyBullet is the simulator actually exercised.
Before submission
- Resolve the project, private registry, storage, and Kubernetes context from supported NPA configuration. A host name is not a project alias.
- Run
npa workbench health preflight --checks nebius,token_factory,s3 --jsonwith the selected project, thennpa workbench health access --capability token_factory --json. TRELLIS is public: do not invent an acceptance flag. - Obtain an operator-private, immutable
REGISTRY/npa-embodiedgen@sha256:<64-hex>image. The tag before resolution must bedev-<full-40-character-NPA-sha>when an operator builds a new image. Consumers use the already-qualified digest from supported configured private delivery; never publish or use a public registry image. - Pass
NEBIUS_TOKEN_FACTORY_KEYonly with--secret-env; it is needed by upstream property estimation and must never be written to YAML, reports, or shell logs. - Use a worker-readable
https://ors3://image URI, never a local path. The workflow base64-transports it through the rendered shell as literal data; reachability and storage permission remain separate prerequisites.
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.
- 10d ago First seen · 96 lines · 42 tokens per session scan A 2b39ba11c484
embodiedgen is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,294 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
godot-optimization
Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.
metashape-reconstruction
Guide dense reconstruction, mesh building, and texturing in Metashape MCP. Covers depth maps, point cloud, mesh, texture, DEM, and orthomosaic generation with correct GPU/CPU settings and quality parameters. Works through the Metashape MCP server.
systemic-emergent-design
Use when designing, auditing, or generating the systemic substrate of a game — the small set of consistent, interacting rules (a "chemistry engine") that produce emergent play, rather than scripted set-pieces. Covers immersive-sim principles (intention & perceivable consequence), multiplicative vs. additive design…
gamebook-screenshot-analysis
Use to ingest Golf GameBook round screenshots (Round Summary + Statistics) into the coach. Extracts a coverage-aware round from the images, self-checks the read, stores it via the gamebook MCP tool (rolling last 5), and returns a normalized summary plus scoring-led progress vs prior rounds. Only score-per-hole is…
digital-twin-builder
Enriches a Universal Assembly Graph (UAG, produced by the game-designer skill) with simulation-grade semantics -- physical units, material/mass properties, and physics/logic constraints -- so it is ready for a physically meaningful digital twin, not just a visual scene. Use this skill whenever the user wants a UAG to…