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 content-agentsgit 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/content-agents)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/content-agents"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/content-agents/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/content-agents"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/content-agents.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 | $0.00050 | $0.01362 |
| Opus 5 | $0.00025 | $0.00681 |
| Sonnet 5 | $0.00010 | $0.00272 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
content-agents 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Agents
Use the Tier 1 content-agents-rigid-object.yaml workflow. Do not add a
first-class service or present upstream Docker Compose as orchestration. NPA's
declarative workflow and SkyPilot own jobs; the public zero-vendor-payload image
runs upstream CLIs and a runtime-fetched isolated OVRTX subprocess.
Boundary
- Accept one customer-owned self-contained USD/USDZ object, or the generated rigid-cube fixture.
- Produce a readable self-contained USDZ, upstream validation evidence,
provenance, and
sim_asset_manifest.jsonfor one Isaac rigid object. - Do not claim arbitrary scenes, articulated robots, joints, generated textures, or Genesis direct-USD consumption.
- Run Material Agent, Physics Agent, and Validation Agent through their real upstream entrypoints. An echo manifest or NPA reimplementation is invalid.
Source and licensing boundary
Use NVIDIA Content Agents v0.5.2 at
36dbf3f274f8e256637230a05a085853f65cc175. Antioch commit
9611fc17a899dee1a2fbf4837cce300019ad7210 was reviewed; do not port it unless a
new failing test proves a current upstream gap.
Content Agents is Apache-2.0. OVRTX 0.3.0.312915 is a proprietary runtime SDK,
not model weights, and must be absent from every public-image layer. On first
render use, fetch the exact architecture-specific wheel directly from NVIDIA's
anonymous package index through upstream's reviewed lock (complete SHA-256
ed582577175e4a5b32f8b69ef9cdbfc3d7337f3786051d8b076e30a2652f6fa5).
NVIDIA's current Omniverse page says downloading or using signifies agreement.
Link the official terms for review, but do not add an NPA acceptance flag,
prompt, stored consent record, or replacement ACCEPT_* variable:
https://docs.omniverse.nvidia.com/connect/latest/common/NVIDIA_Omniverse_License_Agreement.htmlhttps://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/
What ships with it
1 file 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.
- yesterday Changed 83b80e442714
- 5d ago First seen · 106 lines · 50 tokens per session scan A 6582c3168586
content-agents is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,362 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
repro-enforcer
Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.
hpc-foundations
Navigate foundational HPC knowledge across concepts, architectures, schedulers, Linux usage, storage and RDMA, containers, cloud basics, and cluster administration patterns distilled from hpclib.com. Use when the task is about understanding or explaining HPC basics, Slurm or PBS or LSF concepts, Linux-on-cluster…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
ngs-pipeline-management
Next-generation sequencing pipeline management with Snakemake and Nextflow. Use for building, running, and debugging reproducible NGS workflows for RNA-seq, WGS, ChIP-seq, ATAC-seq, and amplicon sequencing. Covers pipeline design patterns, HPC/cloud execution, containerization, and workflow optimization.
pipeline-chipseq
Execute ENCODE ChIP-seq processing pipeline from FASTQ to peaks and signal tracks. Child of pipeline-guide. Provides stage-by-stage Nextflow execution with Docker containers and cloud deployment. Use when users need to process ChIP-seq data following ENCODE standards, run peak calling with MACS2, perform IDR analysis…