Running Autonomous Agent Loop

v20260716

autopilot-loop

This utility executes an autonomous, iterative loop, simulating a comprehensive agent workflow. It systematically manages tasks by checking current status, predicting the optimal next action using specialized tools, executing the required task (e.g., coding, testing), logging the progress, and scheduling the next iteration. It supports task discovery from multiple sources, including team tasks, swarm tasks, and file checklists, ensuring continuous, automated progress towards a defined goal.

Autopilot Automation Agent Workflow Development Scheduling Task Management

Get Skill

261 downloads

Overview

Run one autopilot iteration using Claude Code's native /loop:

Check status: mcp__plugin_ruflo-core_ruflo__autopilot_status
If all tasks complete or max iterations reached, call mcp__plugin_ruflo-core_ruflo__autopilot_disable and stop
Get prediction: mcp__plugin_ruflo-core_ruflo__autopilot_predict for the optimal next action
Execute the predicted task (spawn agent, edit code, run tests, etc.)
Log via mcp__plugin_ruflo-core_ruflo__autopilot_log
Schedule next: ScheduleWakeup({ delaySeconds: 270, reason: "next autopilot iteration" })

Cache-Aware Scheduling

Always use delay 270s (under 300s cache TTL) to keep the prompt cache warm between iterations.

Task Sources

Autopilot discovers tasks from:

team-tasks: Claude Code TaskList entries
swarm-tasks: MCP task_list entries
file-checklist: Markdown checkbox items in tracked files

Configure: mcp__plugin_ruflo-core_ruflo__autopilot_config({ taskSources: ["team-tasks", "swarm-tasks"] })

Info

Category Development

Name autopilot-loop

Version v20260716

Size 1.39KB

Source ruvnet/ruflo

Updated At 2026-07-18