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 workbench-reference-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/workbench-reference-workflows)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/workbench-reference-workflows"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/workbench-reference-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/workbench-reference-workflows"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/workbench-reference-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 | $0.00041 | $0.02445 |
| Opus 5 | $0.00020 | $0.01222 |
| Sonnet 5 | $0.00008 | $0.00489 |
| Haiku 4.5 | $0.00004 | $0.00245 |
Grade A, and why
workbench-reference-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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbench Reference Workflows
The supported, customer-facing catalog and source of truth is the
npa.workflowspec set underworkflows/. The old raw SkyPilot task catalog has no remaining templates. Raw SkyPilot YAMLs may still exist only as guarded tool-specific examples or resource profiles, not as workflow authoring surfaces. SkyPilot remains the engine that executes rendered specs.
The catalog has exactly two workflow directories: workflows/main/ contains
sim2real.yaml, paidf-cosmos3.yaml, and nurec-reconstruct.yaml;
workflows/testing/ contains all other catalog specs.
Keep catalog documentation in workflows/README.md and
add new reference workflows under workflows/testing/.
When To Use
Use this skill for repository workflow YAMLs, runner scripts, cookbooks, artifact contracts, and customer-adaptable pipeline implementations.
Procedure
- Start from the closest checked-in
npa.workflowspec underworkflows/. - Reuse a toolRef from
npa/src/npa/orchestration/npa_workflow/catalog.py; add missing behavior to the workbench tool rather than implementing it again in a runner. - Keep the runner thin. Python runners materialize config, call the workflow submission helper, and report artifacts; the spec owns the stage graph.
- Keep all input and output paths configurable and run-scoped through S3. Stages run in separate pods and cannot depend on a repository-relative path.
- Declare the output the tool actually writes. Extend
test_spec_declared_outputs.pywhen a tool exposes a result-URI helper. - Run
validate-spec, thenplan-spec --run-id preview, before live submit. Register every shipped spec inSUBMIT_LIVE_MATRIX.
Current Reference YAMLs
The retired catalog path is machine-checked by
npa/tests/guardrails/test_skypilot_catalog_retirement.py, so a raw template
cannot quietly reappear there.
No raw SkyPilot templates remain in the retired catalog. Author workflow examples
as npa.workflow/v0.0.1 specs under
workflows/testing/.
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.
- yesterday Changed · +1 lines 476f41002393
- 3d ago Changed · +6 lines 9ee4373c7bea
- 4d ago Changed · +5 lines 6fdfa0b473a3
- 9d ago First seen · 155 lines · 41 tokens per session scan A 88a9e2b33fd1
workbench-reference-workflows is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 2,445 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 2026-09-03.
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…