autonomous-agent-harness

Automate persistent Claude Code agents with memory, cron scheduling, and task queues.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/richardnpaul/everything-vscode-copilot --skill autonomous-agent-harness-richardnpaul
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autonomous-agent-harness
Source: https://github.com/richardnpaul/everything-vscode-copilot/tree/main/.github/skills/autonomous-agent-harness
Command: npx skills add https://github.com/richardnpaul/everything-vscode-copilot --skill autonomous-agent-harness-richardnpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transform Claude Code into a framework for building persistent, self-directing agents with memory, scheduling, and automated workflows. It enables continuous operation and autonomous decision-making without relying on external Hermes/AutoGPT-like runtimes.

Core Features & Use Cases

  • Persistent memory and knowledge graph integration to maintain context across sessions.
  • Schedule-driven execution (crons) to automate routine tasks and workflows.
  • Remote dispatch and computer-use capabilities for event-driven automation and automated testing.
  • Task queue for durable, cross-session work management and orchestration.
  • Use Case: Build a self-running assistant that monitors a project, runs repetitive checks, and updates memory with results.

Quick Start

Initialize the Autonomous Agent Harness to spin up a persistent Claude Code agent that manages memory, schedules tasks, and executes automated workflows.

Frequently Asked Questions about autonomous-agent-harness

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

FAQPage Schema
How do I create a persistent Claude Code agent for long-running workflows?

You can create a persistent Claude Code agent by initializing the autonomous agent harness, which sets up memory storage, cron-based scheduling, and a task queue for hands-free continuous operation across sessions.

What is autonomous scheduling and memory storage for Claude Code agents?

Autonomous scheduling and memory storage allow a Claude Code agent to maintain context across sessions and execute routine tasks automatically via cron-based workflows without requiring external runtimes.

Can I use cron-based scheduling and remote dispatch for automated testing with Claude Code?

Yes, the harness supports cron-based scheduling and remote dispatch with computer-use capabilities, enabling event-driven automation and automated testing for self-directing agents.

How do I build a self-running assistant that monitors a project and updates memory with results?

Initialize the harness to create a self-running assistant that monitors your project, runs repetitive checks, and automatically updates its persistent knowledge graph memory with the results.

Do I need external AutoGPT-like runtimes for autonomous decision-making with Claude Code?

No, you do not need external AutoGPT-like runtimes; the harness transforms Claude Code into a standalone framework with a task queue and guardrails for autonomous decision-making.

What are the limitations of using a task queue for cross-session work management in Claude Code?

The task queue provides durable cross-session work orchestration with built-in guardrails and error handling, but complex external task coordination may require careful configuration to avoid dispatch conflicts.