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-skills-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-skills-guide)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-skills-guide"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-skills-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-skills-guide"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-skills-guide.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 | $0.00077 | $0.01864 |
| Opus 5 | $0.00039 | $0.00932 |
| Sonnet 5 | $0.00015 | $0.00373 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
nemoclaw-skills-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 today.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NemoClaw Skills Guide
NVIDIA NemoClaw runs OpenClaw always-on assistants inside hardened OpenShell sandboxes with NVIDIA inference (Nemotron). It provides CLI tooling, guided onboarding, a security blueprint, routed inference, and workspace management.
This guide lists every agent skill shipped with NemoClaw, organized by audience. Load the specific skill you need after identifying it here.
Skill Buckets
Skills are grouped into three buckets by audience. The prefix in each skill name indicates who it is for.
nemoclaw-user-* (1 skill)
For end users operating a NemoClaw sandbox. Covers routing human users' AI agents to the canonical NemoClaw Markdown documentation.
nemoclaw-maintainer-*
For project maintainers. Covers the daily maintainer cadence, trusted E2E dispatch, continuous E2E maintenance, runtime-provider integration and qualification, Launchable validation, workflow policy, CI failure classification, CI performance analysis, pull request value-stream analysis, documentation refactors, releases, review selection, comparison, triage, security review, and stale bug verification.
nemoclaw-contributor-* (6 skills)
For contributors to the NemoClaw codebase.
The lifecycle runs from checkout setup through planning, implementation, and publication.
Each stage has one owner: nemoclaw-contributor-plan-issue refines an issue into capability slices,
nemoclaw-contributor-implement-issue implements a slice and owns its tests, and
nemoclaw-contributor-create-pr publishes the branch and follows CI and automated review.
Load nemoclaw-contributor-update-dependencies for a dependency upgrade and
nemoclaw-contributor-update-docs for documentation catch-up.
The dependency workflow runs inside the implementation stage.
Component-specific guidance lives with the package it describes, not in a skill.
What ships with it
1 file 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.
- today Changed bcc9679a24d5
- 7d ago Changed · +2 lines 1c250584bd1e
- 11d ago First seen · 107 lines · 77 tokens per session scan A 78f2584e3f46
nemoclaw-skills-guide is a skill published in the GitHub repository NVIDIA/NemoClaw (22,427 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 1,864 once invoked, about $0.0004 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
frontend-conventions
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.
typescript-expert
TypeScript expert for type system, generics, utility types, and strict mode patterns.
app
A skill-management module for storing, organising, sharing, and managing reusable skills, including their descriptions, content, tags, and files.
openclaw-security-checker
A security checker for OpenClaw installations, including their configuration, permissions, containers, network access, and logs.
qveris
Discover and call third-party API capabilities through QVeris, using inspect or probe only when their checks are needed, then generate production REST code. Use when task fit, data quality/freshness, provider comparison, fallback, or the user request favors QVeris.
qveris-cli
Use QVeris CLI to discover and call third-party API tools when task fit, data quality/freshness, provider comparison, fallback, or the user request favors QVeris.