NemoClaw AGENTS.md

A set of project instructions for NVIDIA NemoClaw, an open-source stack for running always-on AI agents inside more isolated OpenShell sandboxes.

In plain words
What is it for?
Understanding NemoClaw work, checking whether an integration or other product change has been approved, and following its validation requirements.
Why use it?
It helps agents follow the project's scope, architecture, security expectations, and approval rules before making product-level changes.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/nvidia/nemoclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/NemoClaw

Made for: Codex, OpenCode.

Per session 4,214 This file is loaded in full into every session.
When invoked 4,214 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04214 $0.04214
Opus 5 $0.02107 $0.02107
Sonnet 5 $0.00843 $0.00843
Haiku 4.5 $0.00421 $0.00421

Measured 3d ago against content hash 10cf7daea60c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

NemoClaw AGENTS.md 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 3d 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.

AGENTS.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Project Overview

NVIDIA NemoClaw is an open-source reference stack for running always-on AI agents such as OpenClaw and Hermes inside NVIDIA OpenShell sandboxes more safely. It provides CLI tooling, a blueprint for sandbox orchestration, and security hardening.

Status: Active development. Interfaces may change without notice.

Product Scope Gate

Technical correctness, passing tests, and green CI do not establish product approval. Before implementing or approving a change that creates a supported integration, solution recipe, custom image, third-party stack, or other product surface, confirm that an accepted issue or design decision establishes the scope and that ownership, lifecycle, compatibility, security, and validation expectations are defined. The recorded decision must be Accept before implementation begins. The record must state the reason, placement, accountable maintainer, and validation plan. Request changes, Defer, and Decline do not authorize implementation. Small documentation corrections and low-risk fixes do not require this decision. If the product decision is missing, do not approve or document the contribution as canonical NemoClaw behavior. Stop and request maintainer direction, or route an independent solution through Community Solutions.

Agent Skills

This repo ships agent skills under .agents/skills/. Use nemoclaw-user-guide for end-user documentation routing, nemoclaw-contributor-* for contributor workflows, and nemoclaw-maintainer-* for maintainer workflows. The contributor lifecycle has one owner for each stage: nemoclaw-contributor-onboard for checkout setup, nemoclaw-contributor-plan-issue for planning, nemoclaw-contributor-implement-issue for implementation and its tests, and nemoclaw-contributor-create-pr for publication and review follow-up. Component-specific guidance belongs in the AGENTS.md file of the package it describes, not in a skill. Load the nemoclaw-skills-guide skill for a full catalog and quick decision guide mapping tasks to skills. Skills that write or review explanatory text must follow the shared Documentation Writing and Review contract.

Read the full file on GitHub · 301 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. 3d ago First seen · 301 lines · 4,214 tokens per session scan A 10cf7daea60c

Subscribe to this mod's changes

NemoClaw AGENTS.md is an instructions file published in the GitHub repository NVIDIA/NemoClaw (22,320 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,214 tokens to every session, about $0.0211 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.