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 physical-ai-data-factorygit 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/physical-ai-data-factory)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/physical-ai-data-factory"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-ai-data-factory/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/physical-ai-data-factory"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-ai-data-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 296 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 298 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 298 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00070 | $0.15139 |
| Opus 5.5 | $0.00028 | $0.06056 |
| Sonnet 5.5 | $0.00014 | $0.03028 |
| Haiku 4.5 | $0.00007 | $0.01514 |
Grade A, and why
physical-ai-data-factory 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 7d 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 — 965 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Physical AI Data Factory (NPA-native, no OSMO)
Source And Attribution
NPA translates NVIDIA's Physical AI Data Factory workflows into native SkyPilot
graphs. The official ecosystem entry point is
https://github.com/NVIDIA/physical-ai-data-factory: it publishes VDA and DIG
agent workflows and links the PAIDF component repositories. The separate
https://github.com/NVIDIA/paidf-orchestration repository is an Apache-2.0
Airflow-on-Kubernetes scaler that publishes the Image Attribute Augmentation and
Event Video Generation DAGs translated here. NPA runtime-fetches their pinned
component/configuration contracts and executes the graphs through SkyPilot;
it does not execute the Airflow controller. Exact revisions and license boundaries
are recorded in skills/NOTICE-NVIDIA-PAIDF.
Earlier design analysis was adapted from https://github.com/NVIDIA/skills,
primarily physical-ai-video-data-augmentation. Copyright (c) 2025-2026 NVIDIA
CORPORATION & AFFILIATES. Upstream licenses: Apache-2.0 and CC-BY-4.0. See
skills/NOTICE-NVIDIA-SKILLS. NPA orchestrates on SkyPilot (not OSMO or Airflow)
and composes existing workbench tools. The separately named direct translations
write an immutable reports/upstream.json source/execution-boundary artifact
before data processing; the two established workflows retained from main are
not textually or behaviorally changed to add that contract.
Workflow Inventory
IAA and EVG's canonical specs and dedicated guides are in
workflows/cosmos-data-factory/. For these two workflows, load shared setup and
the matching NVIDIA-adapted skill from skills/cosmos-data-factory/; their
runbook records which upstream YAMLs require orchestration conversion and which
component configs are reused. The established VDA/DIG paths remain separate.
| YAML | Official source | Classification | Execution |
|---|---|---|---|
physical-ai-data-factory.yaml |
established NPA VDA blueprint | unchanged NPA-native reference | SkyPilot + Transfer 2.5/Token Factory/Curator/FiftyOne |
nvidia-paidf-vda-cosmos-transfer25.yaml |
physical-ai-data-factory VDA | separately named direct semantic translation | SkyPilot + Transfer 2.5/Token Factory/Curator/FiftyOne |
paidf-defect-image-generation.yaml |
physical-ai-data-factory DIG Day-1 manual-ROI | direct scoped translation | SkyPilot + restricted operator-built AnomalyGen compatibility image |
paidf-image-attribute-augmentation.yaml |
paidf-orchestration IAA DAG | direct translation | SkyPilot + operator-built Qwen Edit wrapper + PAIDF protocols |
paidf-event-video-generation.yaml |
paidf-orchestration EVG DAG | direct translation | SkyPilot + operator-built Cosmos3 Super wrapper + PAIDF protocols |
paidf-cosmos3.yaml |
no corresponding Airflow IAA/EVG DAG | NPA-specific VDA alternative | SkyPilot + NPA Cosmos3/Curator/FiftyOne |
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.
- 7d ago Changed · +28 lines f084ac466e12
- 9d ago Changed · +9 lines 5c971ff82199
- 24d ago Changed · +6 lines 70c556c71337
- 27d ago Changed · +11 lines 186e1fe74650
- 28d ago Changed · +20 lines aaceedbbc8c1
- 1mo ago Changed · +2 lines 98f95d6fcb5e
- 1mo ago Changed · +2 lines 5c9a9826be2a
- 1mo ago Changed · +193 lines · -8 tokens per session 897e4c94b25e
- 1mo ago Changed · +9 lines 8a8d1d630bbc
- 1mo ago First seen · 685 lines · 78 tokens per session scan A 19670cf0061b
physical-ai-data-factory is a skill published in the GitHub repository nebius/nebius-physical-ai (105 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 15,139 once invoked, about $0.0003 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 2026-09-03.
physical-ai-data-factory compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| physical-ai-data-factorynebius/nebius-physical-ai | Skill | 105 | today | Apache-2.0 | A | 70 | Claude Code, Codex |
| tensorrt-llmNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 18 | Claude Code, Codex |
| agent-platform-tuninggoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 64 | Claude Code, Codex |
| google-cloud-solution-guided-gke-ai-migrationgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 157 | Claude Code, Codex |
| apigee-agent-gateway-governancegoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 222 | Claude Code, Codex |
| gke-inferencegoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 119 | Claude Code, Codex |
| modalK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 65 | Claude Code, Codex |