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-toolgit 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-tool)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/workbench-tool"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/workbench-tool/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-tool"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/workbench-tool.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 | $0.00035 | $0.00919 |
| Opus 5 | $0.00017 | $0.00460 |
| Sonnet 5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
workbench-tool 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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbench Tool Pattern
This skill is the architectural contract. For the procedures built on it:
- Adding a tool end to end:
skills/workflows/add-workbench-tool/SKILL.md - Writing the CLI and SDK:
skills/atomic/npa-cli-conventions/SKILL.md - Wiring it into a workflow:
skills/atomic/toolref-argv-contract/SKILL.md - Validating before you push:
skills/atomic/pre-pr-validation/SKILL.md
Every workbench tool is a containerized FastAPI service. The container is the unit of deployment; the service endpoint is the unit of invocation; the CLI and SDK are clients.
Each capability must have one source of truth. Put behavior in the service or shared implementation layer, then have all access paths call it. Never duplicate training, inference, import, or status logic separately across API, CLI, and SDK layers.
Three Access Modes
- API: HTTP endpoints exposed by the FastAPI service.
- CLI:
npa workbench <tool> .... - SDK:
npa.sdk.workbench.<tool>.
Standard Endpoints
Workbench services should expose these standard surfaces unless a tool-specific skill documents an exception:
GET /healthPOST /trainorPOST /runGET /statusGET /system-infoGET /list
Deployment
Resolve the endpoint for the operator's explicitly selected artifact bucket
through the supported private configuration. Pass that verified endpoint when
deploying or configuring a tool; do not inherit another cluster's regional
endpoint. Prove the selected bucket and credentials together with
health-preflight before provisioning or submitting.
Kubernetes namespace split:
workbench: deployed workbench services.default: SkyPilot task pods.
Cross-Tool Data Flow
Tools communicate through S3, never by directly calling each other for data transfer. All tool commands must support --input-path and --output-path so pipelines can pass S3 URIs across stages.
Exception / gotcha: a few tools historically use --input-uri / --output-uri
instead (e.g. npa workbench cosmos2 transfer, cosmos3 reason). When you wire a
tool into an npa.workflow toolRef (npa/src/npa/orchestration/npa_workflow/catalog.py),
the argv template MUST match that tool's actual CLI option names and include
required flags (e.g. --run-id). A mismatch passes validate-spec/plan-spec
but crashes on real submit with an unknown-option error. Verify against the CLI
signature, and keep catalog.py and docs/workbench/npa-workflow-tool-catalog.md
in sync. Prefer standardizing new tools on --input-path/--output-path.
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.
- 3d ago Changed · +21 lines 28f9f400f385
- 4d ago Changed · +4 lines 72d5ca98c64f
- 8d ago First seen · 60 lines · 35 tokens per session scan A 2c5877e0ede9
workbench-tool is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 919 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
apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
enterprise
Enterprise-grade systems with microservices, Kubernetes, Terraform, and AI Native methodology. For multi-feature initiatives spanning a release timeline, combine with /sprint master-plan (v2.1.13) to group features into a single 8-phase sprint container with shared scope/budget and 4 auto-pause triggers…
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
spring-boot-project-creator
Creates and scaffolds a new Spring Boot project (3.x or 4.x) by downloading from Spring Initializr, generating package structure (DDD or Layered architecture), configuring JPA, SpringDoc OpenAPI, and Docker Compose services (PostgreSQL, Redis, MongoDB). Use when creating a new Java Spring Boot project from scratch…
chatwoot
Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.