Autopilot Loop
- 662 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
autopilot-loop is a Claude Code skill that runs one autonomous `/loop` iteration using claude-flow autopilot MCP tools to check progress, execute the next task, and schedule the following wake.
About
autopilot-loop is a skill from ruvnet/ruflo that executes a single autonomous loop iteration in Claude Code. Each pass calls `mcp__claude-flow__autopilot_status`, stops with `autopilot_disable` when tasks finish or max iterations hit, fetches the next action from `autopilot_predict`, executes that work, then schedules another wake via native `/loop`. Allowed tools include autopilot_status, autopilot_predict, autopilot_log, autopilot_progress, autopilot_disable, ScheduleWakeup, and Agent. Developers reach for it when long tasks need self-correction without constant prompting. The skill composes Claude Code looping with ruflo autopilot telemetry.
- Persistent autonomous agent loop that runs observe-plan-act cycles
- Self-correction and memory management across iterations
- Reduces context-window fatigue by maintaining long-running tasks
- Works with Claude Code, Cursor, and compatible agent hosts
- 4-step core loop: observe → plan → act → reflect
Autopilot Loop by the numbers
- 662 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,479 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill autopilot-loopAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 662 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you run autonomous agent loops in Claude Code?
Let an agent continuously observe, plan, act, and self-correct in a persistent loop without constant prompting.
Who is it for?
Claude Code users running ruflo autopilot who need self-paced observe-plan-act iterations across long tasks.
Skip if: One-shot prompts without Claude Code `/loop` or environments lacking claude-flow autopilot MCP tools.
When should I use this skill?
User invokes autopilot loop, asks for autonomous iteration, or wants agent self-correction across scheduled wakes
What you get
Completed autopilot tasks, progress logs, and scheduled next-loop wake events
- Executed autopilot tasks
- Autopilot progress logs
- Scheduled loop wake events
Files
Run one autopilot iteration using Claude Code's native /loop:
1. Check status: mcp__claude-flow__autopilot_status 2. If all tasks complete or max iterations reached, call mcp__claude-flow__autopilot_disable and stop 3. Get prediction: mcp__claude-flow__autopilot_predict for the optimal next action 4. Execute the predicted task (spawn agent, edit code, run tests, etc.) 5. Log via mcp__claude-flow__autopilot_log 6. 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__claude-flow__autopilot_config({ taskSources: ["team-tasks", "swarm-tasks"] })
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What does autopilot-loop do each iteration?
autopilot-loop checks claude-flow autopilot_status, disables autopilot if work is done, calls autopilot_predict for the next action, executes that task, then schedules the next Claude Code `/loop` wake through ScheduleWakeup.
Which tools does autopilot-loop use?
autopilot-loop allows mcp__claude-flow__autopilot_status, autopilot_predict, autopilot_log, autopilot_progress, autopilot_disable, ScheduleWakeup, and the Agent tool to run self-paced autonomous coding iterations.