recursive-agents

Implement recursive agent development with K-line theory for knowledge reuse.

1|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/ThinkThoughtThunk/recursive-agents --skill recursive-agents
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recursive-agents
Source: https://github.com/ThinkThoughtThunk/recursive-agents/tree/main
Command: npx skills add https://github.com/ThinkThoughtThunk/recursive-agents --skill recursive-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, typescript, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a framework for LLM coding agents that implements K-line theory, allowing for continuous, autonomous development and leveraging accumulated institutional memory.

Core Features & Use Cases

  • Recursive Execution: Iterative problem-solving with knowledge accumulation across iterations.
  • K-line Theory: Capture and reuse insights as K-nodes for future problem-solving.
  • Level Band Principle: K-nodes connect only to relevant agents within a specific level band.
  • K-Recursion Principle: Efficient memory chains by linking new K-nodes to active K-nodes.
  • Agent Hierarchy: Defined by coordinator, architect, implementer, refactorer, debugger, tester, formatter, and linter roles.
  • Use Case: Imagine you are developing a complex application. Use this Skill to guide the development process, leveraging past knowledge and insights to simplify and streamline the development.

Quick Start

Use the /recursively command to begin a new development task, e.g., /recursively "Implement user authentication with JWT tokens".

Frequently Asked Questions about recursive-agents

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

FAQPage Schema
How do I implement continuous autonomous development with LLM agents?

K-line theory structures institutional memory by capturing insights as K-nodes. The level band principle restricts K-nodes to connect only with relevant agents at specific levels, while K-recursion links new nodes to active ones for efficient memory chains.

Do I need Python and TypeScript to manage agent hierarchies?

Initiate a new development task using the /recursively command followed by your objective. For example, enter /recursively "Implement user authentication with JWT tokens" to start iterative problem-solving with knowledge accumulation.

What is the best way to retain knowledge across complex software iterations?

K-line theory structures institutional memory by capturing insights as K-nodes. The level band principle restricts K-nodes to connect only with relevant agents at specific levels, while K-recursion links new nodes to active ones for efficient memory chains.

How do I start an autonomous development task using recursive execution?

Yes, Python and TypeScript are required dependencies to manage the agent hierarchy and knowledge retention. The hierarchy includes defined roles like coordinator, architect, implementer, refactorer, debugger, tester, formatter, and linter.