Create a read-only action plan for a website
The agent generates a grounded, read-only plan for a specific request against a public website, including evidence, risks, and confirmation requirements.
How it works
Read-onlyOperations and infrastructure
The agent uses plan_site_action to create a grounded, read-only plan for a user's request against a specific domain. The tool automatically indexes the site if needed. The output includes evidence, risks, confirmation requirements, and a durable receipt. This is strictly read-only and does not execute actions.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Prompt for Create a read-only action plan for a website
Create a grounded, read-only plan for interacting with the GitHub repository agentready-mcp using the plan_site_action tool.MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
plan_site_action(domain, request) Automatically indexes a public site when needed, then creates a grounded, read-only plan with evidence, risks, confirmation requirements, and a durable receipt.Connect AI agents to any website — AgentReady