NVIDIA/NemoClaw is an open-source reference stack for running supported AI agents inside NVIDIA OpenShell sandboxes with managed inference, network policies, integrations, snapshots, and lifecycle controls. It is used to run agents such as OpenClaw, Hermes, and LangChain Deep Agents with administrative and security controls. Catalogue add-ons guide coding agents through NemoClaw workflows.
Borrowing it
Nothing to install: this file belongs to NVIDIA/NemoClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA/NemoClaw/main/.agents/skills/nemoclaw-maintainer-runtime-provider/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/NemoClawWrote 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/nvidia/nemoclaw/nemoclaw-maintainer-runtime-provider)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-runtime-provider"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-runtime-provider/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/nvidia/nemoclaw/nemoclaw-maintainer-runtime-provider"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-runtime-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00063 | $0.00980 |
| Opus 5 | $0.00032 | $0.00490 |
| Sonnet 5 | $0.00013 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
nemoclaw-maintainer-runtime-provider 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Managed Runtime Provider
Add one provider through the repository's runtime-provider contract. Keep generic orchestration independent of provider implementations and provider names.
Confirm Product Scope
Apply the product scope gate in AGENTS.md before implementation or approval. Require an accepted
issue or accepted design decision that defines ownership, lifecycle, compatibility, security, and
validation. A valid bundle or passing test does not establish a supported surface.
Keep the portable experimental profile independent. Do not change portable selection, lifecycle, or compatibility behavior as part of a native managed-provider change.
Load Current Authority
Before planning, editing, or reviewing:
- Read
src/lib/onboard/runtime-provider/contract.tsandregistry.ts. - Read
activation.ts,current.ts, andnative-qualification-authority.ts. - Read the candidate provider factory and its provider-owned helpers.
- Trace
SandboxEntry.openshellDriverthrough onboarding and every lifecycle action in scope. - Read the focused contract, activation, provider, architecture, and E2E-support tests.
Use checked-in source and tests as behavior authority. Use these references for interpretation:
- Read Bundle API Contract before changing a provider bundle.
- Read Activation and Qualification before making a provider production-selectable.
- Read Implementation and Review before editing generic orchestration, planning validation, or reviewing a provider PR.
Choose the Delivery State
Name the intended state before coding:
- Candidate bundle: The registry accepts one complete 14-surface object. Optional surfaces may
declare
supported: falsewith a reason. The provider is not production-selectable. - Activated provider: Every required surface and qualification field passes the current
activation contract. The provider enters through
createCurrentRuntimeProviderBundles(...). - Activation-contract extension: The provider topology cannot satisfy the current activation contract. Stop implementation until maintainers accept the contract change and its validation.
- Review: Evaluate the claimed state only. Do not turn an incomplete candidate into an activated provider during review.
What ships with it
4 files 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.
- 2d ago Changed d1fcde6a019c
- 13d ago First seen · 97 lines · 63 tokens per session scan A 6860a2330323
nemoclaw-maintainer-runtime-provider is a skill published in the GitHub repository NVIDIA/NemoClaw (22,442 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 980 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
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…
walkeros-understanding-development
Use when contributing to walkerOS, before writing code, or when unsure about project conventions. Covers build/test/lint workflow, XP principles, folder structure, and package usage.
extending-hobby-smoke-tests
Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…
hogli
PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to run/build/test/lint, or any dev environment commands.