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 npa-cli-conventionsgit 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/npa-cli-conventions)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/npa-cli-conventions"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/npa-cli-conventions/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/npa-cli-conventions"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/npa-cli-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 114 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.
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 | $0.01486 |
| Opus 5 | $0.00025 | $0.00743 |
| Sonnet 5 | $0.00010 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
npa-cli-conventions 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 10d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npa CLI And SDK Conventions
Conventions for changing the npa package itself. For the full path of adding a
new tool, use skills/workflows/add-workbench-tool/SKILL.md.
The codebase is mixed: some modules predate the current pattern. Where this skill and an existing module disagree, follow this skill and leave the old module alone unless you are deliberately migrating it.
Where Code Goes
Behavior belongs in npa/src/npa/workbench/<tool_snake>/. The CLI and SDK are
clients of it, not second implementations. Three integration patterns exist:
- Workbench module first — the SDK builds a Pydantic request and calls the
shared implementation, or HTTP when
service=True. This is the pattern for new work. Seenpa/src/npa/sdk/workbench/dataset.py. - CLI wrapper —
make_cli_wrapperinnpa/src/npa/_sdk.pyexposes an existing CLI callback as an SDK function. Used by older orchestration-heavy tools such as LeRobot. Do not choose it for new tools. - Direct module import — for platform code with no service, such as
npa/src/npa/sdk/provisioning.py.
Registration
Register new command groups under npa workbench in
npa/src/npa/cli/workbench/__init__.py. Do not add top-level groups: the
platform utilities registered in npa/src/npa/cli/main.py predate the solution
namespace model and are marked as legacy in that file.
Options
The cross-tool handoff flags are --input-path (reads an s3:// URI) and
--output-path (writes one). Validate them with the shared contract in
npa/src/npa/cli/path_contract.py. Public handoff paths must not require
VM-local paths, file:// URIs, or plain HTTP URLs. A few legacy tools use
--input-uri / --output-uri; keep them working with aliases rather than
spreading the older spelling.
Conventional flags: -p/--project for the config alias, -n/--name for the
workbench instance, --endpoint to override a saved endpoint, --service to
call the deployed service instead of running in-process, and --token-env for
the env var holding a bearer token. Not every tool has all of them; check the
sibling module rather than assuming.
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.
- 10d ago First seen · 135 lines · 50 tokens per session scan A 34143d93f1b9
npa-cli-conventions 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 1,486 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…