Autonomous Agent Harness

This turns Claude Code into a persistent autonomous agent using only native features and MCP servers. Instead of running standalone frameworks like AutoGPT or Hermes, you get scheduled crons, computer use, persistent memory via knowledge graphs, and task queues that survive sessions. The architecture is clever: dispatch for remote triggers, MCP memory server for structured storage, and regular markdown files for project context. Use it when you want Claude to run things daily, monitor continuously, or build a self-directing assistant that remembers what happened last week. The consent boundaries are explicit, you can dry-run before going live, and it replaces an entire category of tools with what's already built into Claude Code.

skills.sh installs: 4K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --skill autonomous-agent-harness --agent claude-code

Installs into .claude/skills of the current project.

Files

Autonomous Agent Harness

Combine Claude Code's session tools with separately configured scheduling, memory, and computer-use integrations. This is a setup pattern, not a bundled always-on runtime.

Consent and Safety Boundaries

Autonomous operation must be explicitly requested and scoped by the user. Do not create schedules, dispatch remote agents, write persistent memory, use computer control, post externally, modify third-party resources, or act on private communications unless the user has approved that capability and the target workspace for the current setup.

Prefer dry-run plans and local queue files before enabling recurring or event-driven actions. Keep credentials, private workspace exports, personal datasets, and account-specific automations out of reusable ECC artifacts.