Add a browser review checkpoint before risky agent actions with AgentClick

Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.

Prerequisites

AgentClick, browser access, npm, compatible local agent that can invoke tools and follow skill instructions

Installation

Use the upstream install or setup path that matches your environment:

• git clone https://github.com/agentlayer-io/AgentClick.git
• npm install
• npm run dev
• npm run build

Requirements and caveats from upstream:

• For OpenClaw in particular, use a stronger model with solid instruction-following, since the workflow is skill-based and depends on the agent following routing instructions reliably.

Basic usage or getting-started notes:

• AgentClick works as a skill / plugin for modern AI agents. Any agent that can run local tools, send HTTP requests, and follow skill instructions can integrate with it.

• Source: https://github.com/agentlayer-io/AgentClick

• Extracted from upstream docs: https://raw.githubusercontent.com/agentlayer-io/AgentClick/HEAD/README.md

Documentation

• https://github.com/agentlayer-io/AgentClick

Source

• Agent Skill Exchange