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 contribute-workbench-imagegit 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/contribute-workbench-image)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/contribute-workbench-image"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/contribute-workbench-image/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/contribute-workbench-image"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/contribute-workbench-image.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 | $0.00048 | $0.00913 |
| Opus 5 | $0.00024 | $0.00456 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
contribute-workbench-image 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribute A Workbench Image
Keep source contribution, trusted building, and supported release promotion as separate approval boundaries. Public development pushes are irreversible public disclosures even when their tags are later deleted.
Governing Rules
Before acting, read:
skills/atomic/audit-container-docs/SKILL.mdskills/atomic/secure-image-build/SKILL.mdskills/atomic/solution-licensing/SKILL.mdskills/atomic/third-party-eula-preflight/SKILL.mdskills/atomic/build-and-push-image/SKILL.mdskills/atomic/testing-conventions/SKILL.mddocs/workbench/container-packaging.mddocs/workbench/container-image-catalog.mddocs/workbench/contributing-a-containerized-solution.md
Use npa/.venv/bin/python. Keep live infrastructure identifiers, credentials,
and customer data out of commits, workflow inputs, logs, and PR prose.
Contributor Boundary
An external contributor supplies reproducible code and evidence in an
unprivileged fork. Never expose official package credentials to fork-controlled
code or run untrusted code in privileged pull_request_target/workflow_run
jobs. Maintainers rebuild the reviewed commit through the repository workflow.
Add or update the Dockerfile/build script, packaging contract, image resolver and version source, CLI/SDK/workflow surfaces, golden evaluation, tests, docs, and relevant skill together. Use non-root final stages, digest-pinned bases when resolvable, and runtime fetch for gated or non-redistributable material.
Classify source, baked runtime, weights, data, caches, and outputs separately.
Only redistribution: public images may enter official GHCR. Restricted images
remain build-your-own in an operator registry.
Trusted Public Development Build
After review, build the exact trusted full SHA with the manual
publish-public-images.yml workflow on a ref whose code contains that workflow:
gh workflow run publish-public-images.yml \
--ref <reviewed-branch> \
-f dry_run=true \
-f development_sha=<full-git-sha> \
-f build_development_tools=<tool> \
-f tool=<tool>
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.
- 8d ago First seen · 96 lines · 48 tokens per session scan A 04e89505c88c
contribute-workbench-image is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 913 once invoked, about $0.0002 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 2026-09-03.
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.