git:20260710.2925510 to git:20260710.62afd0f
16 added, 15 removed. Audit B to A.
---
- title: "Add a browser review checkpoint before risky agent actions with AgentClick"
+ name: "Add a browser review checkpoint before risky agent actions with AgentClick"
+ slug: "add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick"
description: "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."
+ github_stars: 22
verification: "security_reviewed"
source: "https://github.com/agentlayer-io/AgentClick"
author: "agentlayer-io"
publisher_type: "organization"
- category:
- - "Code Quality & Review"
- framework:
- - "Multi-Framework"
+ category: "Code Quality & Review"
+ framework: "Multi-Framework"
tool_ecosystem:
github_repo: "agentlayer-io/agentclick"
github_stars: 22
npm_package: "@harvenstar/agentclick"
npm_weekly_downloads: 9
---
# 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
- Choose whichever fits your setup:
+ 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
- 1. Copy this skill folder into your local skills directory.
- 2. Clone the repo and symlink or copy the skill into your agent workspace.
- 3. Add the repo as a git submodule if you manage shared skills centrally.
- 4. Install it through your internal provisioning or packaging workflow.
- 5. Download the folder directly from GitHub and place it in your skills collection.
+ 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.
- Install command or upstream instructions:
+ 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.
- ```
- Install with `npm install -g @harvenstar/agentclick`, run `agentclick`, open the local UI in a browser, and instruct your compatible agent to use AgentClick whenever a richer review step is needed before execution.
- ```
+ - 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](https://agentskillexchange.com/skills/add-a-browser-review-checkpoint-before-risky-agent-actions-with-agentclick/)