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-event-video-generationgit 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-event-video-generation)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/physical-ai-event-video-generation"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-ai-event-video-generation/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-event-video-generation"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/physical-ai-event-video-generation.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 | $0.00045 | $0.00750 |
| Opus 5.5 | $0.00018 | $0.00300 |
| Sonnet 5.5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
physical-ai-event-video-generation 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event Video Generation on NPA
Use workflows/cosmos-data-factory/paidf-event-video-generation.yaml.
Read shared setup and the
EVG guide.
Route clothing-image editing to IAA and video-to-video appearance augmentation
to the separate PAIDF VDA workflow.
Preserve all twelve states: provenance → prepare images → sample configs → Cosmos3 Super service plus PAIDF augmentation → validate media → detection/tracking → captions → anomaly Visual QA → person Visual QA → attribute search → dataset assembly → terminal reopening. Do not invent generation-only or labeling-only DAG variants. Service and batch share one state; upstream component retries and failure results remain enforced.
Require an authorized S3 prefix containing selected seed images; a flat directory
makes source mapping clear. NPA enumerates prefixes recursively, does not
implement Airflow's max_images, and does not accept its HTTP/single-object
input forms. There is no implicit demo. Preparation verifies dimensions/decoding,
creates RGB JPEG, and retains source/prepared hashes. Stage the requested subset.
Use existing num_augmentations and seed controls. Event/environment sampling
is defined in the reviewed adapter; arbitrary upstream distribution JSON or
service-mode payloads are not NPA config. Keep the exact Cosmos3 Super
Image2Video revision and private generation/labeling digests. Generation requires
two B200s on one node; captioning/anomaly VQA retain GPU requests for CUVID
decoding even with a hosted VLM.
Retain enabled request guardrails, exact offline snapshots, source-bound
tokenizer/guardrail adaptations, and runtime lineage. Preserve ten-image VQA
controls and request_media_contract; the guide records the upstream
16-frame/12-crop difference. Do not disable guardrails or claim complete QA
coverage merely from successful protocol validation.
Validate/plan with intended overrides. For requested execution, follow the
guide's capability/image gates, submit --runtime, and monitoring with the same
run ID. Read anomaly_dataset/dataset.json, every labeling handoff/sidecar,
upstream provenance, and terminal validation. Decode generated MP4s and inspect
whether the event occurred. Report QA answer coverage/warnings separately from
protocol success. Trackless scenes may omit only supported track-dependent PAS
artifacts. Raw video and separately produced Rerun recordings are distinct evidence.
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.
- 9d ago First seen · 56 lines · 45 tokens per session scan A 4084f39ea103
physical-ai-event-video-generation is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 750 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 2026-10-13.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…