nemoclaw-setup

nemoclaw-setup is a skill for Claude Code from jezweb/claude-skills. It costs 91 tokens per session (3,035 once invoked), scanned D, original, MIT.

A setup guide for NVIDIA NemoClaw, a sandboxed platform for running OpenClaw AI agents with restricted system and network access. It also configures Docker, OpenShell, and optional Cloudflare remote access on Linux.

In plain words
What is it for?
Use it to install NemoClaw, create its sandbox, configure NVIDIA models, and optionally expose it through a Cloudflare tunnel.
Why use it?
It helps avoid the many installation, container, authentication, and known-issue steps involved in getting the platform running safely.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Part of the integrations plugin — 9 skills, 8 commands shipped together

Good fit Use it to install NemoClaw, create its sandbox, configure NVIDIA models, and optionally expose it through a Cloudflare tunnel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jezweb/claude-skills/nemoclaw-setup
Install

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.

Any agent
npx skills add jezweb/claude-skills --skill nemoclaw-setup
Clone the repo
git clone --depth 1 https://github.com/jezweb/claude-skills

Made for: Claude Code.

Or install integrations, the plugin that ships this one along with the rest of its 9 skills, 8 commands.

Wrote 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.

agentmods badge for nemoclaw-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/jezweb/claude-skills/nemoclaw-setup/github.svg)](https://agentmods.dev/skills/jezweb/claude-skills/nemoclaw-setup)
Your own site
<a href="https://agentmods.dev/skills/jezweb/claude-skills/nemoclaw-setup"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/nemoclaw-setup/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.

agentmods 80×15 button for nemoclaw-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/jezweb/claude-skills/nemoclaw-setup"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/nemoclaw-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 14 May 2026
  • Snyk fail 14 May 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.03035
Opus 5 $0.00046 $0.01517
Sonnet 5 $0.00018 $0.00607
Haiku 4.5 $0.00009 $0.00303

Measured 7d ago against content hash 252a27a61efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

nemoclaw-setup scanned grade D with 3 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| Docker | `docker ps` | `sudo apt install docker.io` |

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://nvidia.com/nemoclaw.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://nvidia.com/nemoclaw.sh | bash
plugins/integrations/skills/nemoclaw-setup/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NemoClaw Setup

Install NVIDIA NemoClaw — a sandboxed AI agent platform built on OpenClaw with Landlock + seccomp + network namespace isolation. Runs inside Docker via k3s (OpenShell).

What You Get

  • Sandboxed AI agent with web UI and terminal CLI
  • Powered by NVIDIA Nemotron models (cloud or local)
  • Network-policy-controlled access to external services
  • Optional remote access via Cloudflare Tunnel

Prerequisites

Requirement Check Install
Linux (Ubuntu 22.04+) uname -a
Docker docker ps sudo apt install docker.io
Node.js 20+ (22 recommended) node --version nvm install 22
NVIDIA GPU (optional but recommended) nvidia-smi
NVIDIA API key https://build.nvidia.com/settings/api-keys

Workflow

Step 1: Pre-flight Checks

# Check Docker
docker ps 2>/dev/null || echo "Docker not running or no access"

# Check Node.js
node --version

# Check if already installed
which nemoclaw && nemoclaw --version
which openshell && openshell --version

If nemoclaw is already installed, skip to Step 4.

Step 2: Install NemoClaw

curl -fsSL https://nvidia.com/nemoclaw.sh | bash

This installs NemoClaw and OpenClaw via npm globally (to ~/.npm-global/bin/).

If the installer can't find Node.js, install it first:

curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt install -y nodejs

Step 3: Install OpenShell

curl -LsSf https://raw.githubusercontent.com/NVIDIA/OpenShell/main/install.sh | sh

Installs to ~/.local/bin/openshell.

Step 4: Fix Docker Permissions and cgroup

Docker group — the user must be in the docker group:

sudo usermod -aG docker $USER
newgrp docker
# or log out and back in

cgroup v2 fix — required for k3s inside Docker:

# Check if needed
grep cgroup2 /proc/filesystems && echo "cgroup v2 detected — fix needed"

# Apply fix (needs sudo)
sudo $HOME/.npm-global/bin/nemoclaw setup-spark

Read the full file on GitHub · 329 lines

Changes

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.

  1. 7d ago First seen · 329 lines · 91 tokens per session scan D 252a27a61efb

Subscribe to this mod's changes

nemoclaw-setup is a skill published in the GitHub repository jezweb/claude-skills (1,000 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 3,035 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

proxmox-cluster-ops

Operate a Proxmox VE cluster safely — read-only inspection with pvesh/pct/qm/pvecm instead of hand-editing a live guest, node-by-node package updates that respect quorum, and the shape of joining a new node to an existing cluster. Use when inspecting cluster or guest state, planning a rolling update across cluster…

dryvist/claude-code-plugins · 89 tokens

infra-deploy

Cal.com self-hosted deployment to GCP Cloud Run with Supabase PostgreSQL. Docker Compose for local dev.

terrylica/cc-skills · 27 tokens

cloud-browser-automation

Use cloud browser services (Browserbase) for Cloudflare bypass, JavaScript rendering, and stealth scraping when local tools fail.

kevinnft/ai-agent-skills · 29 tokens

deploying-applications

Deployment patterns from Kubernetes to serverless and edge functions. Use when deploying applications, setting up CI/CD, or managing infrastructure. Covers Kubernetes (Helm, ArgoCD), serverless (Vercel, Lambda), edge (Cloudflare Workers, Deno), IaC (Pulumi, OpenTofu, SST), and GitOps patterns.

ancoleman/ai-design-components · 75 tokens

security-hardening

Reduces attack surface across OS, container, cloud, network, and database layers using CIS Benchmarks and zero-trust principles. Use when hardening production infrastructure, meeting compliance requirements, or implementing defense-in-depth security.

ancoleman/ai-design-components · 48 tokens

kubectl-basics

A guide to kubectl, the command-line tool used to manage Kubernetes clusters, which run containerized applications.

chaterm/terminal-skills · 15 tokens