What is agent-workflow-operate?

A procedure for checking whether a prepared NPA agent virtual machine can create, validate, plan, provision, and run workflow files. A virtual machine is a remote computer used to execute the work.

Use it to verify bootstrapped agent machines and their ability to operate NPA workflows.

It tests the actual autonomous execution environment instead of assuming that a developer machine's test suite proves the agent can operate remotely.

agent-workflow-operate — Skill for Claude Code and Codex by nebius

Install

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.

Any agent

npx skills add nebius/nebius-physical-ai --skill agent-workflow-operate

Clone the repo

git clone --depth 1 https://github.com/nebius/nebius-physical-ai

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/agent-workflow-operate/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/agent-workflow-operate)

Your own site

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/agent-workflow-operate"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/agent-workflow-operate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/agent-workflow-operate"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/agent-workflow-operate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,016 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 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 18
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.
high Privilege Escalation · line 81
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 36
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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00036	$0.01016
Opus 5	$0.00018	$0.00508
Sonnet 5	$0.00007	$0.00203
Haiku 4.5	$0.00004	$0.00102

Measured 8d ago against content hash 5c1921535b59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-workflow-operate 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 8d 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.

skills/workflows/agent-workflow-operate/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Workflow Operation

Operating Model

The workflow operation contract is provider-neutral. The caller owns any reasoning system it uses; NPA does not select or require a model for draft, validation, planning, provisioning, submission, or observation. See docs/workbench/agent-workflow-operations.md for the bounded command journey.
Dev/operator VM is the source of truth for NPA lifecycle, auth, SSH keys, and agent records. Run npa agent fresh-setup, bootstrap, status, and verify-live there.
NPA agent VM is the autonomous workbench execution surface. After bootstrap, it must have staged ~/.npa/config.yaml, ~/.npa/credentials.yaml, Nebius CLI/profile or token material, and the NPA checkout needed to validate, plan, provision, and run workflow YAMLs.
Do not use the dev VM full pytest suite as the acceptance test for agent autonomy. The relevant check is whether the agent VM can operate workflows with its bootstrapped config.

Test Framework

Run the framework by SSHing from the dev VM into the active agent VM using the agent record SSH key. Do not print credential files or secret values.

On the dev VM, resolve the active agent:

npa/.venv/bin/npa agent status --project <project> --name <name> --json

From the dev VM, SSH to the agent public IP with the recorded key and create a temporary apiVersion: npa.workflow/v0.0.1 YAML. Use a known catalog toolRef such as workbench.vlm_eval.run and include all config tokens required by the tool template, including vlm_backend.

On the agent VM or through the agent API, validate and plan:

npa/.venv/bin/npa workbench workflow validate-spec /tmp/spec.yaml --json
npa/.venv/bin/npa workbench workflow plan-spec /tmp/spec.yaml --run-id agent-smoke --json
npa/.venv/bin/npa workbench workflow run-spec /tmp/spec.yaml \
  --run-id agent-smoke --plan-only --scheduler-plan --json

Equivalent API checks:

Read the full file on GitHub · 94 lines

Changes

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.

8d ago First seen · 94 lines · 36 tokens per session scan A 5c1921535b59

Subscribe to this mod's changes

agent-workflow-operate is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,016 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.

Building agents Cloud DevOps and cloud

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…

google/skills · 83 tokens

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).

google/skills · 73 tokens

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…

google/skills · 181 tokens

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".

microsoft/skills · 78 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

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…

Jeffallan/claude-skills · 71 tokens