Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

autopilot-loop — Claude Code skill: autonomous iterations

A skill that runs one iteration of an autonomous loop: checks progress, picks the next task, schedules the next wake. Use it when you want Claude to keep working without manual breaks between tasks.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add ruvnet/ruflo --skill autopilot-loop -a claude-code
Open on GitHub

What autopilot-loop does

autopilot-loop pulls tasks from three sources: Claude Code task lists, MCP servers, and checklist items in files. Each iteration checks status with mcp__plugin_ruflo-core_ruflo__autopilot_status, gets a prediction for the next action from mcp__plugin_ruflo-core_ruflo__autopilot_predict, executes it, and logs the result.

The loop stops when all tasks finish or max iterations are reached. Between wakeups, the skill waits 270 seconds to keep the prompt cache warm and save tokens. Tools available: status check, prediction, logging, progress tracking, loop disable, and wakeup scheduling.

Task sources are configured via mcp__plugin_ruflo-core_ruflo__autopilot_config. You can narrow it down to team-tasks and swarm-tasks only if file-checklist is not needed.

What it helps with

  • Run an agent on long-running work without manual intervention
  • Alternate between status checks, task execution, and scheduling
  • Keep the prompt cache warm across iterations to save tokens
  • Collect tasks from different sources into one queue

Example prompts for the agent

  • /autopilot-loop
  • run the next autopilot iteration
  • execute one loop cycle with status check

How to install autopilot-loop

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill autopilot-loop -a claude-code

2Manually: put the files in place

~/.claude/skills/autopilot-loop/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/autopilot-loop/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

bailian-cli modelstudioai Skill for managing Aliyun Bailian and DashScope resources via the bl CLI. It routes app calls, quota lookups, and knowledge base queries. Claude Code CX Codex Cursor +1 18,700installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. Claude Code CX Codex 282,859installs stitch-loop official google-labs-code Guides agents through iterative website creation with Stitch MCP. The agent reads the baton file, generates UI, integrates the page, and prepares tasks for the next run. Claude Code CX Codex Cursor +1 56,300installs improve shadcn Surveys any codebase in read-only mode and writes self-contained implementation plans for other models to execute. Helps audit bugs, tech debt, and security without touching code. Claude Code CX Codex Cursor +1 37,500installs typesafe-ai typesafe-ai Guides agents on integrating TypeSafe Decision Models like Jev, answering typed questions about state with calibrated probabilities instead of brittle prompts. Claude Code CX Codex Cursor +1 95,600installs

Questions about autopilot-loop

How do I install autopilot-loop in Claude Code?

Run npx skills add ruvnet/ruflo --skill autopilot-loop -a claude-code. The skill will appear in ~/.claude/skills/autopilot-loop/SKILL.md.

What does autopilot-loop do?

One cycle: checks task status, predicts the next optimal action, executes it, and schedules the next wakeup after 270 seconds.

Why exactly 270 seconds delay?

It stays under the prompt cache TTL of 300 seconds, so Claude keeps context between iterations and uses fewer tokens.

Source text

SKILL.md · MIT 
---
name: autopilot-loop
description: Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake
argument-hint: ""
allowed-tools: mcp__plugin_ruflo-core_ruflo__autopilot_status mcp__plugin_ruflo-core_ruflo__autopilot_predict mcp__plugin_ruflo-core_ruflo__autopilot_log mcp__plugin_ruflo-core_ruflo__autopilot_progress mcp__plugin_ruflo-core_ruflo__autopilot_disable ScheduleWakeup Agent
---
Run one autopilot iteration using Claude Code's native /loop:

1. Check status: `mcp__plugin_ruflo-core_ruflo__autopilot_status`
2. If all tasks complete or max iterations reached, call `mcp__plugin_ruflo-core_ruflo__autopilot_disable` and stop
3. Get prediction: `mcp__plugin_ruflo-core_ruflo__autopilot_predict` for the optimal next action
4. Execute the predicted task (spawn agent, edit code, run tests, etc.)
5. Log via `mcp__plugin_ruflo-core_ruflo__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__plugin_ruflo-core_ruflo__autopilot_config({ taskSources: ["team-tasks", "swarm-tasks"] })`

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor