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 audit-container-docsgit 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/audit-container-docs)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/audit-container-docs"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/audit-container-docs/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/audit-container-docs"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/audit-container-docs.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 | $0.00066 | $0.01438 |
| Opus 5 | $0.00033 | $0.00719 |
| Sonnet 5 | $0.00013 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
audit-container-docs 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 9d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Container Documentation
Separate repository intent from registry state. An image can have a Dockerfile, be eligible for redistribution, or exist in a private registry without being in the public release inventory. State only the layer that the evidence proves.
Required Onboarding Hook
Load this skill before finishing any change that introduces or changes a
workbench image or an image-backed solution. This includes work performed through
contribute-workbench-image, add-workbench-tool, and
oss-solution-registry-onboard.
Reconcile docs/workbench/container-image-catalog.md after the image name, pin,
packaging classification, and publication intent are stable:
- Add or update a table row only when the image is selected by
publicly_publishable_tools()(which excludes publication quarantine) and its exact resolved tag is anonymously pullable. Do not list a build, private-registry artifact, or merely redistribution-eligible image as published. - For a new solution that remains BYOF-only, restricted, internal, deferred, or otherwise outside the public plan, do not force it into the public table. Confirm the exclusion against repository sources and document it in the appropriate solution or container documentation when the distinction would otherwise be misleading.
- Treat the catalog audit and its guardrail as part of the originating image or solution change, not as optional follow-up work.
Read The Authoritative Sources
Read AGENTS.md, skills/index.yaml, and the applicable image/tool skills first.
Use these sources for distinct facts:
npa/docker/workbench/packaging-contract.yaml: built-image inventory, packaging tier, ports, security exceptions, and redistribution eligibility.npa/src/npa/deploy/images.py: canonical tool-to-image names, restricted tools, public-release membership, and tag-resolution exceptions.npa/pyproject.toml[tool.npa.supported-tools]: default immutable image pins.npa/src/npa/deploy/*_image_manifest.json: variant-specific pins and evidence for SONIC, Wan, LeRobot, and any future manifest-backed tool.npa/src/npa/deploy/public_release_manifest.json: accepted release tags and exact anonymously verifiedpublished_digestvalues.npa/docker/workbench/<image>/Dockerfile*, build scripts, lock files, and redistribution records: what an image actually contains and does.npa/src/npa/deploy/publish_public.py: exact public source-to-target plan.- Golden evaluations, CLI/SDK code, and workflow specs: capability and runtime integration. Do not infer capabilities from an image name alone.
- Anonymous registry manifest/config inspection: what is publicly pullable now. Treat this as volatile observed state, not a replacement for repository intent.
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.
- 9d ago First seen · 126 lines · 66 tokens per session scan A f5c4d4a0fca1
audit-container-docs is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,438 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.