autonomous-loops

Community

Orchestrate Claude Code loops—from simple to DAGs

Authorgiuseppecutuli
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Patterns and architectures for running Claude Code autonomously in loops, enabling hands-off development across simple pipelines to RFC-driven multi-agent systems.

Core Features & Use Cases

  • Supports sequential pipelines, NanoClaw REPL sessions, infinite agent loops, continuous Claude PR loops, and RFC-driven DAG orchestration.
  • Provides guidance on when to use each pattern, with practical examples and best practices for safe autonomous execution.
  • Emphasizes context persistence, quality gates, and merge-queue strategies to manage complexity and risk.

Quick Start

Give Claude a RFC-style spec and let the system decompose and execute the loop pipeline autonomously.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: autonomous-loops
Download link: https://github.com/giuseppecutuli/speakdoc/archive/main.zip#autonomous-loops

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.