agent-loop

Official

Orchestrate autonomous multi-step problem solving

AuthorEntelligentsia
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The agent-loop pattern enables autonomous multi-step reasoning where the LLM must observe, think, act, and iterate until a goal is met. It is designed for tasks that cannot be solved with a single prompt and where the next action depends on outcomes of previous steps.

Core Features & Use Cases

  • Supports observe-think-act cycles with termination guardrails to prevent runaway loops.
  • Enables ReAct and Plan-and-Execute architectures with optional context management and re-planning.
  • Useful for complex data gathering, decision-making, procedural automation, and tool orchestration in software systems.

Quick Start

Provide a task that requires autonomous multi-step reasoning and let the agent loop through observe, think, and act until completion.

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: agent-loop
Download link: https://github.com/Entelligentsia/skillforge/archive/main.zip#agent-loop

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.