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-user-guide/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-user-guide)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-user-guide"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-user-guide/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-user-guide"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-user-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00029 | $0.00700 |
| Opus 5.5 | $0.00012 | $0.00280 |
| Sonnet 5.5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
nemoclaw-user-guide 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 1mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NemoClaw Docs for AI Agents
Use the canonical NemoClaw documentation as your source of truth. Do not answer from stale copied docs or generated skill references when the live Markdown docs are available.
Retrieval Order
- If the NemoClaw docs MCP server is already configured, use its read-only
searchDocstool to find task-relevant docs. - Otherwise, use the Markdown index and pages below. Docs lookup does not require installing or configuring MCP.
- If MCP is not available, fetch the AI documentation index first:
https://docs.nvidia.com/nemoclaw/llms.txt. - Fetch the specific
.mdpage listed in the index or returned by docs search for the user's task. - If you only find an HTML documentation URL, replace the
.htmlsuffix with.md, or append.mdto the route when the URL has no suffix. - Prefer the user's selected agent variant. Do not mix variant-specific instructions unless you explain why.
Optional setup and starting pages
Read Docs Access when the user requests MCP configuration or when starting an installation needs direct links for the selected agent variant. Ordinary docs questions can use the index without reading that reference.
How to Help the User
- Use the selected agent variant from the request or current sandbox. Ask when it cannot be determined and changes the instructions. Check the selected release's support status, including Pi activation.
- Ask only for missing operating-system, provider, model, endpoint, policy, or channel choices that affect the requested task.
- Run commands within the user's requested scope and the environment's permissions. Explain material effects; request authorization only for effects outside that scope.
- Summarize important command output instead of asking the user to paste terminal output into chat.
- Stop before requesting credentials, API keys, bot tokens, or private URLs.
- Never ask the user to paste secrets into chat.
- Use redacted placeholders such as
<PASTE_YOUR_API_KEY_HERE>in examples.
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.
- 1mo ago Changed · -24 lines · -69 tokens per session 9a03288b91ab
- 2mo ago First seen · 77 lines · 98 tokens per session scan A 48899df7cdc8
nemoclaw-user-guide is a skill published in the GitHub repository NVIDIA/NemoClaw (22,871 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 700 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
pentest-ctf-binary
Binary exploitation (Pwn) and reverse engineering tools for CTF challenges and software analysis.
pentest-ctf-forensics
Digital forensics, steganography, and packet analysis for CTF challenges and investigation.
OpenClaw 网络优化助手
A Chinese-language guide for diagnosing and safely improving a computer’s network, including DNS, proxies, VPNs, and routing. DNS translates website names into network addresses; a proxy or VPN routes traffic through another service.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
cli-wiring
Bug class: Commands implemented in packages/squad-cli/src/cli/commands/ but never routed in cli-entry.ts.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…