meow:lazy-agent-loader

Community

Load agents on demand to cut token usage.

Authorngocsangyem
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This approach reduces token waste by deferring full agent loading until an agent is activated, keeping summaries lightweight at startup.

Core Features & Use Cases

  • On-demand loading of agent definitions to save tokens during multi-agent workflows.
  • Summary-first indexing with full definitions loaded only for PRIMARY candidates.
  • Session-level caching to avoid re-loading and to preserve context across interactions.
  • Seamless integration with agent-detection to minimize context expansion while preserving accuracy.

Quick Start

Use the lazy-agent-loader to load agents on demand during a session to minimize token usage.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: meow:lazy-agent-loader
Download link: https://github.com/ngocsangyem/MeowKit/archive/main.zip#meow-lazy-agent-loader

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.