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 diagram-to-npa-workflowgit 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/diagram-to-npa-workflow)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/diagram-to-npa-workflow"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/diagram-to-npa-workflow/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/diagram-to-npa-workflow"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/diagram-to-npa-workflow.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 | $0.00081 | $0.02031 |
| Opus 5 | $0.00041 | $0.01015 |
| Sonnet 5 | $0.00016 | $0.00406 |
| Haiku 4.5 | $0.00008 | $0.00203 |
Grade A, and why
diagram-to-npa-workflow 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram → NPA Workflow
When To Use
Load when the input is a picture of a pipeline (architecture diagram, boxes +
arrows + decision diamonds) and/or a numbered step write-up, and the output
must be a runnable npa.workflow/v0.0.1 spec under
workflows/testing/ (or a skill/example directory).
This skill is the front end that produces the graph. It composes two existing skills — read them too:
skills/workflows/author-npa-workflow/SKILL.md— spec contract + validation hardening.skills/workflows/generate-npa-workflow/SKILL.md— beauty conventions + design recipe.
Reference material for this skill:
reference/mapping.md— keyword→toolReftable, control-flow patterns, the sim2real worked example, and discrepancy-reconciliation rules.- The real Sim2Real composition is the canonical
workflows/main/sim2real.yaml; do not regenerate a stub-toolRef twin from the historical diagram. examples/av-failure-mode-from-diagram.yaml— a second, differently-shaped diagram (linear, multi-resource, no loop) proving the method generalizes.
Inputs → Output Contract
| Input | You extract |
|---|---|
| Diagram image | Nodes (boxes), edges (arrows), decision diamonds, back-edges (loops), fan-in/out |
| Step write-up | Per-step: actor/tool, input artifact, output artifact, loop membership, gate/threshold |
| Domain knowledge | Which catalog toolRef implements each node; where real GPUs are needed |
Output: one apiVersion: npa.workflow/v0.0.1, kind: Workflow document that
passes validate-spec and plan-spec.
Procedure
Work the seven steps in order. Do not skip validation.
1. Build the step table (data, not prose)
For every numbered step in the write-up, record a row:
step# | short name | tool/actor | input artifact | output artifact | loop? | gate/threshold?
Missing/duplicate step numbers are expected — the write-up and diagram will
disagree. Reconcile with the rules in reference/mapping.md ("Reconciling
discrepancies"): the diagram is authoritative for topology (what connects to
what, where the loops are); the write-up is authoritative for intent
(thresholds, why a step exists, which tool). Record every reconciliation as a
one-line # note: comment near the affected state so reviewers see the decision.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 a603c9f1cb11
- 8d ago First seen · 162 lines · 81 tokens per session scan A 6d33df72eb21
diagram-to-npa-workflow is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 2,031 once invoked, about $0.0004 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…