nemoclaw-user-manage-policy

Manage NemoClaw sandbox egress by adding, removing, or modifying allowed network endpoints.

Updated May 23, 2026
One-click install
npx skills add https://github.com/yo-steven/skills-exploration-20260522 --skill nemoclaw-user-manage-policy-yo-steven
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nemoclaw-user-manage-policy
Source: https://github.com/yo-steven/skills-exploration-20260522/tree/main/skills/NemoClaw/nemoclaw-user-manage-policy
Command: npx skills add https://github.com/yo-steven/skills-exploration-20260522 --skill nemoclaw-user-manage-policy-yo-steven

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of getting a NemoClaw sandbox to reach only the right external endpoints by managing its sandbox egress policy.

Core Features & Use Cases

  • Static policy changes: Edit the baseline policy blueprint so endpoint access persists after sandbox recreation.
  • Dynamic policy updates: Add or remove endpoint access on a running sandbox without restarting, using preset-format merges.
  • Interactive approvals: Review and approve blocked requests in OpenShell’s TUI for one-off access decisions.
  • Integration-focused workflows: Apply maintained presets or author custom presets for common tools and internal services.

Quick Start

Use the nemocalw command to apply an existing preset to a running sandbox by running: nemoclaw my-assistant policy-add pypi --yes

Frequently Asked Questions about nemoclaw-user-manage-policy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage egress control for a NemoClaw sandbox?

You can manage NemoClaw sandbox egress by adding, removing, or modifying allowed network endpoints. This Skill supports both persistent baseline policy edits and non-destructive dynamic updates for running sandboxes.

Can I add network endpoints to a running sandbox without restarting it?

Yes, dynamic policy updates allow you to add or remove endpoint access on a running sandbox without restarting. This is achieved using non-destructive preset-format merges via the policy-add command.

How do I apply a preset to a running sandbox?

To apply an existing preset to a running sandbox, use the nemoclaw command with policy-add. For example, run 'nemoclaw my-assistant policy-add pypi --yes' to quickly integrate the preset.

What is the difference between static and dynamic sandbox policy changes?

Static policy changes edit the baseline policy blueprint so endpoint access persists after sandbox recreation. Dynamic policy updates apply preset-format merges to a running sandbox without requiring a restart.

Can I interactively approve blocked network requests in NemoClaw?

Yes, interactive approvals let you review and approve blocked requests in OpenShell’s TUI. This allows you to make safe, one-off access decisions for your sandbox endpoints.

Does OpenShell policy interception preserve existing presets?

Yes, safe enforcement is handled through OpenShell policy interception while preserving existing presets. The system uses deterministic merging via policy-add to ensure baseline configurations remain intact.