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 vm-nebius-authgit 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/vm-nebius-auth)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/vm-nebius-auth"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/vm-nebius-auth/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/vm-nebius-auth"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/vm-nebius-auth.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 27 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 | $0.00064 | $0.00533 |
| Opus 5 | $0.00032 | $0.00267 |
| Sonnet 5 | $0.00013 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
vm-nebius-auth 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VM Nebius Authentication
Diagnose before starting login
For a read-only readiness request, use
npa workbench health preflight --checks nebius --json; do not start profile
creation. A failed identity probe alone does not distinguish missing profile
configuration, expired authentication, denied access, or a network failure.
Check the selected profile's presence using the installed CLI's profile help
and non-secret metadata. Do not dump configuration or token values. Report
missing configuration only when established; otherwise leave the cause unknown.
Create or recover a human profile only when the user authorizes login. A successful authentication check does not prove resource-creation permissions, quota, or capacity. Preserve attached-service-account profiles on agent VMs.
Run on the operator/dev VM:
npa/.venv/bin/npa agent auth-profile \
--ssh-host <operator-vm-host> --ssh-user <operator-vm-user> \
--profile <profile>
The command strips ambient IAM-token variables, returns immediately for an
already-authenticated profile, or starts nebius --no-browser profile creation
and its first profile-scoped IAM probe in one PTY (CLI versions may defer OAuth
until first use). When the
CLI advertises exactly one official HTTPS browser URL and one loopback callback,
it prints the URL and an exact local-machine ssh -N -L command using the
runtime-selected port. Run the tunnel locally before opening the URL. Unsafe,
ambiguous, or malformed callbacks fail closed; cancellation and timeout stop the
child flow.
The browser callback completes the CLI profile. NPA then verifies iam whoami
and separately verifies that IAM can mint an access token, with command output
discarded. Never request, paste, print, log, return, or chat the IAM token.
Human interactive authentication is for an operator/dev VM or explicit
recovery. Keep the npa-agent VM on its attached service account and
cursor-sa metadata-token profile by default.
Verify changes with:
npa/.venv/bin/python -m pytest \
npa/tests/unit/test_nebius_vm_auth.py \
npa/tests/cli/test_agent_auth_profile.py -q
What ships with it
1 file 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.
- 3d ago Changed · +14 lines 09a804303c39
- 11d ago First seen · 41 lines · 64 tokens per session scan A 9accb211e2fe
vm-nebius-auth is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 533 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…