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 toolref-argv-contractgit 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/toolref-argv-contract)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/toolref-argv-contract"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/toolref-argv-contract/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/toolref-argv-contract"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/toolref-argv-contract.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 | $0.00050 | $0.01394 |
| Opus 5 | $0.00025 | $0.00697 |
| Sonnet 5 | $0.00010 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
toolref-argv-contract 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The toolRef Argv Contract
A toolRef is the only way an npa.workflow spec invokes a workbench tool. The
engine expands it from TOOL_CATALOG in
npa/src/npa/orchestration/npa_workflow/catalog.py into an argv list and runs
it inside the task pod.
Nothing in validate-spec or plan-spec compares that argv against the CLI
command it will be handed. A template can validate, plan, and render perfectly
and still die with No such option on real infrastructure after a GPU has been
provisioned. npa/tests/guardrails/test_tool_catalog_argv.py exists to close
that gap. Treat it as the real gate, not the spec validators.
Read this before writing an entry, and again whenever you rename or retype a CLI option that any toolRef already passes.
Shape
"workbench.<tool_snake>.<verb>": ToolEntry(
name="workbench.<tool_snake>.<verb>",
description="...",
argv_template=[
"npa", "workbench", "<tool>", "<verb>",
"--input-path", "{{config.input_uri}}",
"--output-path", "{{config.output_uri}}",
],
),
The catalog key is snake_case; the argv inside it is the kebab-case CLI path.
workbench.scenario_gen.generate invokes npa workbench scenario-gen generate.
Rules
Every flag must exist on the target command. Verify against the live
signature, not memory and not the docs. npa workbench <tool> <verb> --help is
the source of truth.
Include required flags. A template missing --run-id or --workflow-run
fails at runtime, not at render.
Never pass a format word to a path option. --output json on an option that
takes a path is the worst failure mode in this class, because the stage
succeeds and the declared artifact silently never appears. When a command has
both, --output takes the path and --output-format takes the word.
Do not pass infrastructure. Image, accelerator, and GPU type belong in the
spec's resources.<profile>, not in the stage argv. Passing them again nests
infrastructure selection inside the pod.
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 eb499852c06f
- 9d ago First seen · 124 lines · 50 tokens per session scan A 2bf004e809bb
toolref-argv-contract is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,394 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…