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 runtime-fetch-onboardgit 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/runtime-fetch-onboard)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/runtime-fetch-onboard"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/runtime-fetch-onboard/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/runtime-fetch-onboard"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/runtime-fetch-onboard.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 | $0.00060 | $0.03188 |
| Opus 5.5 | $0.00024 | $0.01275 |
| Sonnet 5.5 | $0.00012 | $0.00638 |
| Haiku 4.5 | $0.00006 | $0.00319 |
Grade A, and why
runtime-fetch-onboard 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 1mo 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime-Fetch Onboarding
Keep an onboarding moving when third-party bytes cannot be redistributed in a container. Choose either a redistributable launcher that fetches immutable upstream components at runtime under the operator's own access and the applicable upstream terms, or an operator-built derivative that remains confined to a private registry when restricted inputs must be baked.
Runtime fetch is a delivery design, not a license bypass. It can solve a redistribution restriction. It cannot create permission to use software, offer it as a service, violate field-of-use terms, or consume restricted outputs in a forbidden downstream stage.
Load First
skills/atomic/solution-licensing/SKILL.mdto classify all six artifact boundaries.skills/atomic/third-party-eula-preflight/SKILL.mdwhen any download or use depends on terms or gated access.skills/workflows/byof-onboard/SKILL.mdfor the NPA build/run mechanics.skills/atomic/secure-image-build/SKILL.mdbefore building or publishing.
Default Decision
Do not reject an otherwise viable solution merely because its weights, dataset, assets, SDK, or source may not be baked into a distributable image. Choose the narrowest compliant shape:
| Restricted boundary | Containerize | Fetch at runtime | Result |
|---|---|---|---|
| Weights/checkpoints only | Redistributable source, dependencies, and launcher | Exact weight revision/files | Candidate image can remain public if its built bytes pass every publication gate |
| Dataset or task assets | Code and loader | Exact dataset/assets with checksums | Data stays outside the image; its use and output obligations still apply |
| Source as well as weights | Neutral bootstrap/downloader only | Exact source revision plus exact weights | Viable only when the operator is permitted to fetch and run both |
| SDK or runtime | Neutral bootstrap, or build instructions only | SDK/runtime from the vendor, or build the derivative in the operator's registry | Public image is possible only when built layers contain no restricted vendor bytes |
| Base image | Dockerfile/build recipe | Operator pulls and builds in an operator-controlled registry | Build-your-own; do not publish the derived image unless redistribution is independently allowed |
| Outputs, service use, or field of use | Only the permitted capability | Nothing can package this away | Defer or reject the prohibited capability and record the human/vendor decision needed |
| No verified right to fetch or use | Nothing dependent on the artifact | Nothing | Block only the dependent capability until the exact upstream access probe or documented product mechanism succeeds; token presence alone is not evidence |
What ships with it
2 files 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.
- 1mo ago First seen · 255 lines · 60 tokens per session scan A 38a05afbec43
runtime-fetch-onboard is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 3,188 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 2026-09-13.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.