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 architecturegit 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/architecture)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/architecture"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/architecture/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/architecture"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/architecture.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 | $0.00028 | $0.00422 |
| Opus 5 | $0.00014 | $0.00211 |
| Sonnet 5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
architecture 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 2d 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.
What it actually says
Architecture Context
Detailed rationale and the preserved May 2026 architecture snapshot live in
docs/architecture/contributor-context.md.
The platform progression is:
- Tools: Workbench.
- Composition: Platform.
- Intelligence: agentic layer.
The current phase is Workbench, the Tools layer: marketplace model, pay per use, npa CLI/SDK/agents.
The May 2026 snapshot covers LeRobot, FiftyOne, Genesis, Isaac Lab, Cosmos,
LanceDB, GR00T, and SONIC. It is historical context, not the current tool count
or proof that a newly built image works. Resolve current capabilities from the
workflow catalog and skills/index.yaml; resolve image validation and publication
from npa/src/npa/deploy/images.py and
docs/workbench/container-image-catalog.md. New source and replacement digests
need their own real capability and artifact evidence.
SkyPilot is the sole orchestrator. Argo is deprecated.
Partner model: partners listed in the ecosystem must run workloads on Nebius infrastructure when accessed through the platform.
LeRobot connects data generation to robot policy training and is the default training framework for robot policy workflows.
The sim-to-real gap is the most important and least-tooled layer. Existing approaches are either deeply custom or unproductized.
OSS and container packaging
- OSS onboarding ladder (BYOF → workflow → first-class tool):
docs/architecture/oss-onboarding-ladder.md - Container packaging tiers and security baseline:
docs/workbench/container-packaging.md - Machine-readable packaging contract:
npa/docker/workbench/packaging-contract.yaml - Generic BYOF operator skill:
skills/workflows/byof-onboard/SKILL.md(npa workbench byof,npa.sdk.workbench.byof,workbench.byof.repo)
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.
- 2d ago Changed · +1 lines f592098fc3af
- 10d ago First seen · 44 lines · 28 tokens per session scan A 68615e074509
architecture is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 422 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…