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 teardown-and-costgit 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/teardown-and-cost)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/teardown-and-cost"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/teardown-and-cost/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/teardown-and-cost"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/teardown-and-cost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 86 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 | $0.00050 | $0.01635 |
| Opus 5 | $0.00025 | $0.00817 |
| Sonnet 5 | $0.00010 | $0.00327 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
teardown-and-cost 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teardown and cost hygiene
There is no npa cost and no npa quota command. Spend control here is
procedural: run things in an order that cannot orphan resources, and audit for
residue afterwards. The single most expensive mistake is destroying
infrastructure while managed jobs are still running, which leaves jobs billing
against resources nothing is tracking any more.
The ordering is not optional
Cancel workloads, then remove the things that host them, outermost last:
npa workbench workflow cancel <run-id> --project <alias> --json # every run
npa agent destroy --project <alias> --name <name> --yes
npa skypilot cleanup-controller --project <alias> --context <context> --yes
npa cluster down --project <alias> --force
npa storage bucket delete --project <alias> --yes --wait
npa storage service-account delete --project <alias> --dry-run
npa storage service-account delete --project <alias> --yes
npa configure --forget-project <alias>
npa cleanup --full --yes --project <alias>
Cancel is repeat-safe — a run that never launched is a successful no-op — so
there is no reason to skip it. cleanup-controller refuses while managed jobs
are in progress and retries that specific refusal after the queue drains; treat
the refusal as correct, not as something to force.
Deleting the project itself is separately opt-in and stays retained by default:
npa destroy --project <alias> --all --json # plan only
npa destroy --project <alias> --all --yes # execute, project retained
npa destroy --project <alias> --all --delete-project --yes --json
npa destroy --all without --delete-project --yes never deletes the project.
Full details of the ownership gating live in skills/tools/nebius-infra/SKILL.md;
this skill is the operational ordering and the audit.
What is cloud spend and what is only local clutter
Confusing these two wastes time and money in opposite directions.
| Command | Touches cloud spend | Notes |
|---|---|---|
npa cleanup |
No | Local caches and state only, even with --yes |
npa cleanup --full --yes |
No | Also removes saved HF/Token Factory/NGC creds; read-only IAM verification |
npa workbench workflow cancel |
Yes — stops it | Repeat-safe |
npa skypilot cleanup-controller |
Yes | Shared; drains first |
npa cluster down |
Yes | Terraform-managed cluster and its nodes |
npa agent destroy |
Yes | Agent VM and its resources |
npa storage bucket delete |
Yes | Contents and versions included |
npa destroy --all --delete-project --yes |
Yes | Ownership-gated; all three flags required |
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.
- 12d ago First seen · 150 lines · 50 tokens per session scan A 545302ebf9dd
teardown-and-cost is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,635 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 2026-08-30.
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…
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…