npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@akson/cortex-agents

v0.3.0

Published

Comprehensive Claude agent management for @cortex ecosystem

Readme

@akson/cortex-agents

Comprehensive Claude agent management for the @akson ecosystem. Discover, install, and manage Claude Code agents with ease.

Features

🔍 Agent Discovery - Find agents from community sources, Anthropic's library, and custom collections
📦 Easy Installation - Install agents globally or per-project with simple commands
🎯 Smart Suggestions - Get agent recommendations based on your tech stack
🔧 Project Integration - Seamlessly manage project-specific and global agents
Custom Agents - Create and manage your own specialized agents
🔄 Synchronization - Keep project agents in sync with global agents

Installation

npm install -g @akson/cortex-agents

Quick Start

# Initialize agent management for your project
akson-agents init

# Discover agents for your tech stack
akson-agents discover --stack nextjs supabase typescript

# Install a useful agent
akson-agents install sql-expert --source anthropic

# Get suggestions based on your project
akson-agents suggest

# List installed agents
akson-agents list

Commands

Discovery & Installation

# Discover agents with filters
akson-agents discover --stack nextjs,react --category development --rating 4

# Browse agents by category  
akson-agents browse --category marketing

# Install agents from different sources
akson-agents install typescript-expert --source community
akson-agents install api-designer --source anthropic --global

# Install with options
akson-agents install devops-expert --force --global

Management & Organization

# Initialize project agent management
akson-agents init

# List all installed agents
akson-agents list
akson-agents list --global-only

# Sync project with global agents
akson-agents sync

# Get personalized suggestions
akson-agents suggest

Custom Agent Creation

# Create a custom agent
akson-agents create myarmy-order-processor

# Create from template
akson-agents create database-optimizer --template sql-expert

Project Analysis

# Analyze current project
akson-agents analyze

# Get statistics
akson-agents stats

Agent Sources

Community Sources

  • awesome-chatgpt-prompts - Curated community prompts
  • flowgpt - Popular agent marketplace
  • promptbase - Premium tested prompts

Official Sources

  • anthropic - Anthropic's prompt library
  • builtin - @akson curated agents

Custom Sources

  • local - Your custom agents
  • team - Team-specific agents

Project Structure

your-project/
├── .claude/
│   ├── agents/           # Project-specific agents
│   │   ├── config.json   # Project configuration
│   │   ├── custom-agent.md
│   │   └── myarmy-expert.md
│   └── ...
└── package.json

Global agents are stored in ~/.claude/agents/

Configuration

Project configuration in .claude/agents/config.json:

{
  "name": "myarmy-landing",
  "stack": ["nextjs", "supabase", "typescript", "tailwind"],
  "agents": {
    "global": ["sql-expert", "nextjs-expert"],
    "project": ["myarmy-business-expert", "database-migration-expert"]
  },
  "preferences": {
    "autoUpdate": true,
    "suggestAgents": true,
    "categories": ["development", "design"]
  }
}

Agent Format

Agents are stored as Markdown files with YAML frontmatter:

---
name: custom-expert
description: Expert in custom solutions
color: blue
category: development
frameworks: ["TypeScript", "React"]
tags: ["custom", "solutions"]
---

You are an expert in custom solutions...

Your core competencies include:
- Expertise area 1
- Expertise area 2

When helping users, you will:
1. Understand requirements
2. Provide detailed solutions
3. Include relevant examples

API Usage

import { AgentManager } from '@akson/cortex-agents';

const manager = new AgentManager();

// Initialize project
await manager.init();

// Discover agents
const agents = await manager.discover({
  stack: ['nextjs', 'supabase'],
  category: 'development'
});

// Install agent
await manager.install('sql-expert', { 
  source: 'anthropic',
  global: false 
});

// Get suggestions
const suggestions = await manager.suggest();

Integration with @akson Ecosystem

This package integrates seamlessly with other @akson tools:

  • @akson/cortex-cli-analytics - Analytics agents for tracking
  • @akson/cortex-landing-* - Landing page optimization agents
  • @akson/cortex-api-* - API integration specialists

Contributing

  1. Fork the repository
  2. Create your feature branch
  3. Add tests for new functionality
  4. Submit a pull request

License

MIT License - see LICENSE file for details.