Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nebius/nebius-physical-ainpx agentmods add skills/nebius/nebius-physical-ai/first-run-setupWrote 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/first-run-setup)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/first-run-setup"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/first-run-setup/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/first-run-setup"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/first-run-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 43 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 58 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 | $0.00057 | $0.02320 |
| Opus 5 | $0.00028 | $0.01160 |
| Sonnet 5 | $0.00011 | $0.00464 |
| Haiku 4.5 | $0.00006 | $0.00232 |
Grade A, and why
first-run-setup 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First run: zero to a verified result
The failure mode this skill exists to prevent is spending an hour provisioning a GPU cluster and discovering at stage three that a token was never accepted. Each step below has a gate: a command whose success is the precondition for the next step. Do not skip ahead because a later step looks more interesting.
Escalate through the cheapest tier that can prove the thing you need. Most first-run questions are answered before any GPU is involved.
Step 1 — Install and prove the CLI runs
python3 -m venv npa/.venv
npa/.venv/bin/pip install -e "npa[dev]"
npa/.venv/bin/npa --version
Gate: npa --version and npa --help both succeed. They must work with no
Nebius, Hugging Face, NGC, Kubernetes, or S3 credentials at all. If they do not,
the problem is the install, not your cloud setup.
Python 3.10+ is required. Terraform 1.x must be on PATH for anything managed
(npa cluster up, npa agent fresh-setup); pip install -e npa does not install
it. On Windows, work inside WSL2 — the cloud paths assume POSIX.
Use npa/.venv/bin/python and npa/.venv/bin/npa explicitly for repo validation
rather than a bare python or npa from PATH.
Step 2 — Configure Nebius
npa configure --show # inspect the expected layout, writes nothing
npa configure # interactive: creates/reuses the CLI profile
configure writes ~/.npa/config.yaml (machine-managed, non-secret) and
~/.npa/credentials.yaml (secrets, 0600). Interactive setup offers S3 bucket
and access-key provisioning by default. --no-provision is a provider-free
project/token setup: it neither probes nor adopts saved storage. Enter an exact
existing bucket name only when you intend to reuse it; pressing Enter generates
a fresh name with a UTC timestamp and random suffix.
For unattended setup, avoid the prompts entirely:
npa configure --no-interactive --no-provision --save-env-credentials \
--tenant-id <id> --project-id <id> --region <region> --project-alias <alias>
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 · +4 lines 292c52f7b0dd
- 7d ago Changed · +1 lines cfb4dd3ff1f8
- 9d ago First seen · 217 lines · 57 tokens per session scan A 9dfab58ed49c
first-run-setup is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 2,320 once invoked, about $0.0003 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 2026-09-03.
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…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
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".
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…