Use Case
AgentSentinel Safety Layer is a powerful AI agent skill that extends your assistant with new capabilities. Local-first budget and policy guardrails for agent actions, with optional remote sync to AgentSentinel. This guide walks you through installing AgentSentinel Safety Layer, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install AgentSentinel Safety Layer: npx clawhub@latest --dir ~/.claude/skills install agent-sentinel
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to finance & investment to trigger AgentSentinel Safety Layer
Review the output and refine your prompt for better results
Combine AgentSentinel Safety Layer with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing AgentSentinel Safety Layer
Help me get started with AgentSentinel Safety Layer
What can AgentSentinel Safety Layer do for my finance & investment workflow?
Show me an example of using AgentSentinel Safety Layer
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install agent-sentinelOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install agent-sentinelβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/agent-sentinel/π‘Extract and place the folder at the path above, then restart your agent.