Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nebius/nebius-physical-ainpx agentmods add skills/nebius/nebius-physical-ai/oss-solution-registry-onboardWrote 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/oss-solution-registry-onboard)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/oss-solution-registry-onboard"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/oss-solution-registry-onboard/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/oss-solution-registry-onboard"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/oss-solution-registry-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 536 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.
- medium Rogue Agent · line 518 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 611 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00042 | $0.07482 |
| Opus 5 | $0.00021 | $0.03741 |
| Sonnet 5 | $0.00008 | $0.01496 |
| Haiku 4.5 | $0.00004 | $0.00748 |
Grade A, and why
oss-solution-registry-onboard 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 4d 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 — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS Solution Registry Onboard
Use this skill when an agent is asked to turn a public Physical AI repository into a registry/catalog candidate for NPA. This is stricter than generic BYOF: the agent must discover that solution's real documented capabilities, test those capabilities with solution-specific commands, and produce validation evidence before calling the solution registry-ready.
Do not force capabilities into a shared taxonomy. Each OSS project has its own APIs, assets, and hello-worlds; name and test them as the upstream project does.
When To Use
- Onboard a public GitHub/GitLab Physical AI repo into the NPA registry/catalog
- Promote a BYOF image from "containerized repo" to "discoverable NPA solution"
- Evaluate partner or OSS robotics, simulation, perception, policy-training, synthetic-data, or evaluation projects for Workbench inclusion
- Create registry metadata, workflow specs, docs, and validation evidence for an OSS solution
If the task is only "build and run this fork," load
skills/workflows/byof-onboard/SKILL.md. If the task asks for registry/catalog
admission, load this skill and then delegate build/run mechanics to BYOF.
Required Companion Skills
Load these as needed before making decisions:
skills/workflows/byof-onboard/SKILL.md— containerize, push, and run OSS repo workloads through BYOF.skills/workflows/author-npa-workflow/SKILL.md— write and validatenpa.workflow/v0.0.1specs andtoolRefusage.skills/atomic/architecture/SKILL.md— respect the Workbench marketplace and solution namespace boundary.skills/atomic/testing-conventions/SKILL.md— run validation withnpa/.venv/bin/pythonand report exact evidence.skills/atomic/solution-licensing/SKILL.md— satisfy the License admission gate below: classify what the image actually bakes, decide whether it may be redistributed, and record it in the packaging contract.skills/atomic/audit-container-docs/SKILL.md— reconciledocs/workbench/container-image-catalog.mdfor every new or changed image-backed solution without confusing registry admission with public-mirror publication.- Relevant tool skill (
skills/tools/isaac-lab,lerobot,genesis,cosmos,groot,sonic,fiftyone,lancedb,mjlab, orretargeting) when the upstream repo depends on that stack.
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.
- 4d ago Changed 5af618a14404
- 6d ago Changed · +2 lines ecd4a2d4c604
- 9d ago First seen · 613 lines · 42 tokens per session scan A eb3220072071
oss-solution-registry-onboard is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 7,482 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
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger keywords - openshell…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.