Agent Wake for Openclaw

A bridge that allows external scripts and background processes to wake and trigger responses from OpenClaw agents upon task completion.

krisco65
v1.0.1
Mar 2, 2026
0
1k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install agent-wake

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install agent-wake using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Agent Wake?

Agent Wake is a specialized utility designed to bridge the gap between background processes and active AI agent sessions. By utilizing the Openclaw Skills framework, it allows developers to send a wake signal to an agent once an asynchronous task—such as a Claude Code CLI job, a scheduled cron script, or a webhook—concludes.

This utility ensures that agents are not left in the dark about the status of long-running operations and can immediately provide feedback or follow-up actions in the designated communication channel. It solves the common problem of agents being unaware when async work finishes, making it an essential part of the Openclaw Skills ecosystem for automation.

Agent Wake Use Cases

  • Notifying an AI agent immediately after a Claude Code CLI task finishes its execution.
  • Triggering automated agent responses from system cron jobs or background maintenance tasks.
  • Integrating with price alerts or monitoring scripts to alert an agent of market changes or threshold breaches.
  • Automating agent feedback loops within CI/CD pipelines or local software build processes.

How Agent Wake Works

  1. An external process or script finishes its designated background task.
  2. The script executes the Agent Wake Python utility, passing a status message and an optional channel ID.
  3. The utility makes an HTTP POST request to the gateway tools endpoint using the cron tool.
  4. The agent receives the injected notification as a prioritized system message.
  5. The agent processes the event and responds directly in the specified Discord channel with the relevant feedback.

Agent Wake Setup

To begin using this tool within your Openclaw Skills environment, follow these steps:

  1. Ensure the cron tool is enabled for HTTP access within your gateway configuration.
  2. Set the GATEWAY_TOKEN environment variable or place it in a local .env file.
  3. Copy the agent-wake.py script to your project or system path.
  4. Execute the wake command from any CLI:
python agent-wake.py "Task finished -- brief summary" "YOUR_DISCORD_CHANNEL_ID"

Agent Wake Data Schema & Taxonomy

The Agent Wake tool organizes its interactions using a simple yet effective metadata structure to communicate with Openclaw Skills:

Attribute Format Description
Event Message String The text injected into the agent session as a system prompt.
Channel ID String The Discord snowflake ID where the agent is directed to reply.
Auth Method ENV/File Uses GATEWAY_TOKEN via environment variables or .env files.
Tool Trigger HTTP POST Communicates via the /tools/invoke gateway endpoint.

Agent Wake Advanced Features

  • Support for multi-agent environments by targeting specific gateway endpoints for complex Openclaw Skills workflows.
  • Automated channel detection for main session waking without requiring explicit Discord IDs.
  • Seamless integration capabilities with Python subprocesses for inclusion in larger DevOps automation pipelines.
  • Zero-dependency design, requiring only the Python standard library for maximum portability across different server environments.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*