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 nebius-infragit 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/nebius-infra)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/nebius-infra"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/nebius-infra/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/nebius-infra"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/nebius-infra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to high
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 →
- high Privilege Escalation · line 13 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 22 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 164 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 166 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 200 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 235 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 236 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 226 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 239 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 21 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00038 | $0.03402 |
| Opus 5 | $0.00019 | $0.01701 |
| Sonnet 5 | $0.00008 | $0.00680 |
| Haiku 4.5 | $0.00004 | $0.00340 |
Grade A, and why
nebius-infra 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 6d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nebius Infrastructure
When To Use
Use this skill before running NPA workloads that need Nebius runtime settings,
object storage, container registry access, Kubernetes, or GPU routing. Also use
it when reviewing setup changes touching npa configure, npa provision-if-absent, ~/.npa/config.yaml, ~/.npa/credentials.yaml, or
workflow environment variables.
Procedure
-
Keep committed files public-repo safe. Never hardcode project IDs, tenant IDs, registry IDs, bucket names, VM IPs, private endpoints, or secrets.
-
Capture runtime configuration with
npa configure. In CI or scripted contexts, use--showfor the schema and write~/.npa/config.yamlplus~/.npa/credentials.yamlfrom placeholders:npa configure --showInteractive runs auto-provision S3 when a Nebius profile is present. Use
--no-provisionto supply existing object-storage credentials instead. -
Ensure runtime resources with the additive-only setup command:
npa provision-if-absent --project ci --dry-run --skip-validate --output-format jsonReal runs may ensure S3 and Kubernetes. Dry runs only resolve settings and print intended actions. The command must not teardown or replace resources. Storage setup declares
GetObject,HeadObject,PutObject,DeleteObject, andListObjectsV2. The minimum provider binding is bucket-scopedstorage.object-editor, assigned through the project-scopednpa-storage-object-editors-<exact-project-id>group. A provider-verified existing tenanteditorsmembership is accepted for backward compatibility. Creating that broader membership is allowed only as an explicit fallback after the provider reports the narrow role unsupported; unknown or unreadable IAM fails closed before key creation or probing. A newly created or changed binding enables typed propagation convergence even when an active key is reused. Persistent authorization denial is terminal and must retain redacted phase evidence. The explicit opt-in isNPA_ALLOW_EDITORS_STORAGE_FALLBACK=1; never set it merely to bypass an authorization or inventory failure. Credentials and IAM generations are authoritative only underproject_credentials.projects.<exact-project-id>; top-level fields are a selected-project compatibility view. Migrate legacy global state only with exact ownership proof. Its canonical whole-path quota plan treatscompute.disk.size.network-ssdas bytes and reports exact bytes plus GiB, independently ofcompute.disk.count. Unknown, missing, malformed, or contradictory disk-capacity evidence blocks mutation. The default cluster is 1,151 GiB (128 GiB CPU + 1,023 GiB GPU); adding the default 100 GiB agent root disk makes the README whole path 1,251 GiB.
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.
- 6d ago Changed · +1 lines 638957e58b27
- 11d ago First seen · 255 lines · 38 tokens per session scan A 6b573152359b
nebius-infra is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 3,402 once invoked, about $0.0002 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…