autonomous-loops

Orchestrate Claude Code autonomous loops with sequential and parallel steps.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/RUSHYOP/imperium-cli --skill autonomous-loops-rushyop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autonomous-loops
Source: https://github.com/RUSHYOP/imperium-cli/tree/main/content/skills/autonomous-loops
Command: npx skills add https://github.com/RUSHYOP/imperium-cli --skill autonomous-loops-rushyop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Patterns and architectures for running Claude Code autonomously across loops and agent pipelines.

Core Features & Use Cases

  • Loop patterns: Sequential pipelines, nanoClaw REPL, infinite agentic loop, Continuous Claude PR loop, and RFC-driven DAG orchestration.
  • Architectural guidance: RFC-driven decomposition, multi-agent coordination, and deterministic worktrees.
  • Use Case: Orchestrate a multi-step content-generation task with parallel agents and merge queue semantics.

Quick Start

Provide a ready-to-run autonomous loop pattern for Claude Code using the selected pattern.

Frequently Asked Questions about autonomous-loops

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Claude Code in autonomous loops for development pipelines?

To run Claude Code in autonomous loops, you define configurable loop patterns with clear sequential or parallel steps. This orchestrates multi-step execution for development pipelines, research cycles, and iterative content generation.

What is RFC-driven DAG orchestration for agent pipelines?

RFC-driven DAG orchestration is an architectural pattern for decomposing tasks into a directed acyclic graph. It coordinates multi-agent execution within autonomous loops by using RFC definitions to structure and sequence the workflow.

How do I orchestrate parallel agents in a multi-step generation task?

You orchestrate parallel agents by configuring loop patterns that support parallel step execution. This allows multiple agents to process distinct steps simultaneously before merging results via merge queue semantics.

Can I use sequential pipelines and infinite agentic loops together?

Yes, autonomous loop patterns support both sequential pipelines and infinite agentic loops. You configure the execution pattern based on whether your workflow requires linear step progression or continuous iterative processing.

Do I need clear loop definitions to run continuous Claude PR loops?

Yes, continuous Claude PR loops require clear loop definitions loaded into context. Defining the specific pattern and body instructions is necessary to properly orchestrate the automated pull request generation cycle.

What are the limitations of running autonomous agent workflows?

Autonomous agent workflows require clear loop definitions and body instructions loaded into context to function properly. Without deterministic worktree configurations and explicit multi-agent coordination, execution may become unpredictable.