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 team-identitygit 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/team-identity)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/team-identity"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/team-identity/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/team-identity"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/team-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.00968 |
| Opus 5.5 | $0.00012 | $0.00387 |
| Sonnet 5.5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
team-identity 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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbench identity and access
Use this skill for the npa workbench access identity boundary. It is
not a chat-agent routing feature and does not provision a cluster, gateway, or
browser login flow.
Local Workbench accounts are the stable ownership domain. Create an
account_namespace once, then use Accounts for local people and
issue_key_file for a personal mode-0600 key. TeamClient is the supported
agent-callable API for an already-authorized service endpoint. Obtain credentials
through the private saved-session provider or the explicit load_bearer_token
file/environment path. Never print bearer credentials or copy them into reports.
For end users, start with npa login --endpoint <workbench-HTTPS-endpoint> and choose
a privately delivered personal key or --nebius. Successful login saves a
private named connection and unambiguous placement defaults. Use
npa workbench whoami, submit, runs, and run for ordinary execution;
administrators use npa workbench access. The same commands support an individual
or a shared installation. Older npa workbench team commands remain compatible.
submit starts execution and returns a run ID. run RUN_ID shows that existing
run's status by default; --action selects logs, artifacts, cancellation, or
resumption. runs lists the person's runs.
Workbench commands can omit endpoint and credential flags; agents can use
npa.sdk.workbench.team.connect(). A native session asks the official Nebius CLI
for a token on each command without copying IAM tokens into Workbench storage.
If no human profile exists, create an isolated CLI configuration, preserving
the machine's default profile. npa logout forgets the local connection; it
does not revoke the server key, cloud session, or running work.
The CLI retains automatic retry identities before submission. Repeating an
unchanged submission returns its original run. Use --new-run only after an
acknowledged submission when another run is intended; reconcile an unconfirmed
submission first. Explicit idempotency keys remain supported.
On a remote operator VM, --no-browser --ssh-host <alias> emits the verified
official browser URL and scoped loopback callback forward. An authorized agent
may open that URL and establish the tunnel. Let the human complete any required
password or MFA; never request the callback URL or token in chat. Verify actual
human login and a real workload before labeling a demo SSO-verified.
The server's Nebius location does not restrict Kubernetes workload destinations.
Use export-connections to prepare private runtime connections for both server
containers, and run check-clusters from the server environment before a real
workload. EKS uses the image's AWS CLI with separately supplied server profiles;
do not transfer an operator's inline keys or assume laptop SSO works in the pod.
See docs/workbench/external-kubernetes.md. Direct cloud VM execution and native
SkyPilot client protocol access remain outside this boundary. Never label a
Nebius workload or an offline EKS token check as live AWS validation.
An external identity is only a credential for an already-created local account:
- Generic
identityuses the configured JWT issuer and its verified subject. - Native
nebius_identityselects one tenant and optionally one federation. It requiresaccount_namespace, cannot coexist with genericidentity, and verifies each human token at Nebius IAM's fixed ProfileService endpoint. - Use
link_identityonly with the exact configured issuer and the provider-verified immutable subject. There is no auto-enrolment, email match, cloud-group import, or cloud-role-to-Workbench-grant mapping.
Use account unlink with the exact local user, old issuer, and old subject
before replacing an external provider link. It works for a retired issuer or
disabled account, preserves local ownership and keys, and revokes that login
on the next request. It does not cancel already admitted work.
Native Nebius browser SSO happens in the person's Nebius CLI/identity provider.
Workbench only verifies the resulting short-lived IAM bearer token. A linked
account's local groups, grants, allocations, ownership, and disabled state stay
authoritative; local keys remain usable. See
docs/workbench/team-identity.md
for the private token-file and linking contract.
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.
- 11d ago First seen · 76 lines · 31 tokens per session scan A 1c7297deabeb
team-identity is a skill published in the GitHub repository nebius/nebius-physical-ai (50 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 968 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…