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-contributor-onboard/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-contributor-onboard)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-contributor-onboard"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-contributor-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/nvidia/nemoclaw/nemoclaw-contributor-onboard"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-contributor-onboard.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 | $0.00037 | $0.01177 |
| Opus 5.5 | $0.00015 | $0.00471 |
| Sonnet 5.5 | $0.00007 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
nemoclaw-contributor-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 20d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard a NemoClaw Contributor
Use the repository setup script as the executable source of truth. Do not duplicate its dependency, build, hook, CLI-exposure, or readiness logic in agent commands.
Establish Trust First
- Read the root
AGENTS.mdandCONTRIBUTING.mdcompletely. - Inspect the worktree and current branch without discarding or overwriting existing changes.
- Refresh the trusted
origin/mainreference, then compare the entire checkout/worktree diff against that up-to-date base before executing any checkout-local code. Include staged, unstaged, and untracked files; review lockfiles and all transitively executed source, not only the entry script or package manifests. - If an execution surface differs from trusted
origin/main, review the diff before running it. Existing implementation authorization covers in-scope repository-local validation. Isolate candidate code from host credentials and host mutations. This includes setup scripts and installed hooks. Stop before execution if that isolation cannot be established. Ask only for exposure or side effects outside that authorization.
Route by Intent
- Readiness only: run
./scripts/dev-setup.sh --doctorand never run setup, repair, CLI exposure, runtime onboarding, or the pinned agent. Use./scripts/dev-setup.sh --doctor --jsonwhen a machine-readable report helps. - Initial checkout setup: run
./scripts/dev-setup.shfrom the repository root. - Explicit repository repair: run
./scripts/dev-setup.sh --repaironly when the user asks to repair or retry repository-local setup. - CLI exposure: after explicit approval, run
./scripts/dev-setup.sh --expose-cli. - Runtime onboarding: after explicit approval, run
./scripts/dev-setup.sh --with-runtime.
The default and repair modes may update repository-local dependencies, builds, hooks, and the root Python environment.
They must not create a gateway or sandbox or expose a host-visible nemoclaw command.
CLI exposure is an explicit opt-in that may use an npm link or a user-local shim.
What ships with it
2 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.
- 20d ago Changed 507391f49eee
- 1mo ago Changed · +2 lines · -62 tokens per session 3dadc713ee8e
- 2mo ago First seen · 91 lines · 99 tokens per session scan A 3bb0dd75b215
nemoclaw-contributor-onboard is a skill published in the GitHub repository NVIDIA/NemoClaw (22,871 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,177 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 2026-08-30.
Other skills, from other repositories
stripe-best-practices
Guides Stripe integration decisions across development and test environment planning (separate sandboxes vs the shared test mode sandbox), API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax…
ckjia-shopping
A shopping search and price-comparison tool for Taobao, JD.com, Tmall, and Pinduoduo, with image-based product recognition. It requires the ckjia-shopping service and its access key to be enabled.
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
authoring-ci-workflows
Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, timeout-minutes, paths filters, caching, or runner choice. Covers PostHog's workflow-authoring…
qveris
Access third-party professional data and tools through QVeris: find services, review supported scope when needed, call them, and generate production REST code. Use when existing tools are insufficient, a provider is unknown, comparison or fallback is needed, or the user requests QVeris.
app
A skill-management module for storing, organising, sharing, and managing reusable skills, including their descriptions, content, tags, and files.