cam-notify

Process CAM system events using a multi-layered decision model.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/jcyLite/openclaw-plugin-agent-monitor --skill cam-notify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cam-notify
Source: https://github.com/jcyLite/openclaw-plugin-agent-monitor/tree/main/skills/cam-notify
Command: npx skills add https://github.com/jcyLite/openclaw-plugin-agent-monitor --skill cam-notify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill intelligently processes system events from the Code Agent Monitor (CAM), deciding whether to notify users, auto-approve requests, or request human confirmation, ensuring efficient and safe AI agent operation.

Core Features & Use Cases

  • Event Handling: Processes various CAM events like permission_request, waiting_for_input, agent_exited, and error.
  • Decision Making: Implements a three-layer decision model (whitelist, blacklist, LLM judgment) to handle requests based on risk levels.
  • Smart Notifications: Formats messages clearly for users and aggregates notifications to reduce noise.
  • Use Case: When an AI agent needs to execute a bash command, this Skill analyzes its risk. Low-risk commands are auto-approved silently, medium-risk commands are auto-approved with a brief notification, and high-risk commands or critical decisions are flagged for user confirmation.

Quick Start

Use the cam-notify skill to process a received CAM system event payload.

Frequently Asked Questions about cam-notify

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

FAQPage Schema
How do I automate AI agent permission requests and reduce notification noise?

Automate AI agent permission requests by processing CAM system events through a multi-layered decision model that auto-approves low-risk commands silently and aggregates notifications to reduce noise.

What is a multi-layered decision model for AI agent risk assessment?

A multi-layered decision model for AI agent risk assessment uses whitelist, blacklist, and LLM judgment layers to evaluate event payloads and determine appropriate auto-approval or notification strategies.

How to handle waiting for input and agent exit events in event processing?

Handle waiting for input and agent exit events by extracting context from the CAM event payload to format clear user messages and determine if human confirmation is required.

Does cam-notify support high-risk bash command blocking for AI agents?

Yes, cam-notify supports high-risk bash command blocking by flagging high-risk commands and critical decisions for explicit user confirmation instead of auto-approving them.

Can I use cam-notify for notification aggregation and user reply handling?

Yes, you can use cam-notify for notification aggregation and user reply handling to efficiently manage AI agent operations and process user responses to permission requests.