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 skypilot-workflowsgit 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/skypilot-workflows)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/skypilot-workflows"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/skypilot-workflows/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/skypilot-workflows"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/skypilot-workflows.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 | $0.00056 | $0.02735 |
| Opus 5 | $0.00028 | $0.01367 |
| Sonnet 5 | $0.00011 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00274 |
Grade A, and why
skypilot-workflows 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 4d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkyPilot Workflows
For teardown after project/config removal, use the existing immutable teardown
receipt (npa skypilot cleanup-controller --receipt <id> --context <context> --yes). A terminal receipt or exact provider-verified missing cluster is a no-op
without bootstrapping SkyPilot. Otherwise cleanup stays bound to the exact
recorded project/context and preserves local controller state until remote
absence is independently verified. Never fall back to the current kube context
or an unrelated SkyPilot profile.
SkyPilot is the workflow execution engine in this repo. Argo is deprecated; do not add or revive Argo workflows.
SkyPilot is not the repository authoring surface. Pipelines are
npa.workflow/v0.0.1 specs, and the engine plans those specs and renders
SkyPilot tasks. Use skills/workflows/author-npa-workflow/SKILL.md to author a
pipeline. The retired raw-task catalog must not return; raw SkyPilot input is
still accepted for customer-provided tasks and guarded tool-specific examples.
Invocation
SkyPilot lives in an isolated virtualenv outside NPA's main Python environment. Invoke it through NPA_SKYPILOT_BIN; never rely on sky from PATH.
Use npa skypilot bootstrap to create or reuse the pinned SkyPilot 0.12.2
venv, then set NPA_SKYPILOT_BIN="$(npa skypilot status --bin-path)".
The Kubernetes controller is the default path (W9-skypilot-k8s-controller). The VM controller exists only as a fallback.
For workflows that write S3 state or artifacts, supply config.bucket and a
run-scoped config.prefix, even when their declared output URIs are absolute.
NPA_CONFIG_DIR selects NPA configuration; set KUBECONFIG separately to the
verified file containing the selected cluster context. An isolated configuration
must also resolve the authorized S3 endpoint and credentials through supported
private sources or the child process environment. Keep credential values out of
arguments and logs. A successful structural render or --plan-only does not
prove these live submission prerequisites.
Preserve a failed submission intent and inspect the exact run state before
recovering from a preflight failure; do not delete the intent or assume a failed
CLI exit means no launch occurred.
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.
- 4d ago Changed · +22 lines c7fed22312cc
- 5d ago Changed · +55 lines 1a6dc0f0d4cd
- 8d ago First seen · 132 lines · 56 tokens per session scan A 9d7dc961a588
skypilot-workflows is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,735 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…
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…