Autonomous Agent Harness

This turns Claude Code into a persistent autonomous agent by wiring together crons, dispatch, memory, and computer use. Instead of running a separate framework like AutoGPT or Hermes, you schedule recurring tasks that review PRs, monitor deploys, or run daily standups using Claude's native scheduled-tasks MCP server. Memory persists across sessions through both built-in project memory files and the knowledge graph MCP server. The architecture is clever: task queues live in markdown files, cron patterns trigger agent sessions, and computer-use handles browser automation. Best for when you want Claude to keep working between conversations, like nightly test runs or hourly production checks, without spinning up external infrastructure.

skills.sh installs: 1.1K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --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.