debugging-toolkit

Qwen Code Agents: AI-Powered Orchestration and Automation

Adapted for Qwen Code — 77 plugins, 182 agents, 149 skills, and 96 commands now working with Qwen 3.6

A comprehensive production-ready system combining 182 specialized AI agents, 16 multi-agent workflow orchestrators, 149 agent skills, and 96 commands organized into 77 focused, single-purpose plugins — adapted for Qwen Code.

Credits & Attribution

This project is a fork/adaptation of claude-code-workflows by Seth Hobson (@wshobson).

All original plugin content, agent expertise, skill knowledge, command workflows, and architectural design are the work of Seth Hobson and contributors. This adaptation converts the plugin infrastructure to work with Qwen Code instead of Claude Code, while preserving 100% of the original content and intelligence.

Original repository: github.com/wshobson/agents Original license: MIT

---

Why This Exists

Claude Code is expensive. Qwen Code is free (OAuth: 60 req/min, 1000/day) or very cheap (API key). This project brings the same powerful agent orchestration system to Qwen Code so you can use 182 specialized AI agents without paying for Claude.

Before vs After

Aspect	Before (Claude Code)	After (Qwen Code)
Cost	$3+ per 1M tokens (Sonnet)	Free (OAuth) or ~$0.02/1M tokens
Model for critical tasks	Claude Opus 4.6	Qwen-Max
Model for complex tasks	Claude Sonnet 4.6	Qwen-Plus
Model for fast tasks	Claude Haiku 4.5	Qwen-Flash
Plugins	77	77 (same)
Agents	182	182 (same expertise)
Skills	149	149 (same knowledge)
Commands	96	96 (same workflows)
Agent knowledge	Identical	Identical
Skill content	Identical	Identical
Workflow automation	Identical	Identical
Monthly savings	Baseline	~99% cheaper

What Changed vs What Stayed

Component	Changed?	Details
Agent system prompts	No	All 182 agents have identical expertise
Skill knowledge packages	No	All 149 skills with progressive disclosure
Command workflows	No	All 96 workflow automations
Plugin structure	No	Same directory organization
model: opus references	Yes	Mapped to model: qwen-max
model: sonnet references	Yes	Mapped to model: qwen-plus
model: haiku references	Yes	Mapped to model: qwen-flash
Plugin manifest	Yes	plugin.json + qwen-extension.json
Context files	Added	QWEN.md per plugin

Overview

This unified repository provides everything needed for intelligent automation and multi-agent orchestration across modern software development:

• 77 Focused Plugins - Granular, single-purpose plugins optimized for minimal token usage and composability
• 182 Specialized Agents - Domain experts with deep knowledge across architecture, languages, infrastructure, quality, data/AI, documentation, business operations, and SEO
• 149 Agent Skills - Modular knowledge packages with progressive disclosure for specialized expertise
• 16 Workflow Orchestrators - Multi-agent coordination systems for complex operations like full-stack development, security hardening, ML pipelines, and incident response
• 96 Commands - Optimized utilities including project scaffolding, security scanning, test automation, and infrastructure setup

Key Features

• Granular Plugin Architecture: 77 focused plugins optimized for minimal token usage
• Comprehensive Tooling: 96 commands including test generation, scaffolding, and security scanning
• 100% Agent Coverage: All plugins include specialized agents
• Agent Skills: 149 specialized skills following for progressive disclosure and token efficiency
• Clear Organization: 24 categories with 1-10 plugins each for easy discovery
• Efficient Design: Average 3.6 components per plugin (follows Anthropic's 2-8 pattern)

How It Works

Each plugin is completely isolated with its own agents, commands, and skills:

• Install only what you need - Each plugin loads only its specific agents, commands, and skills
• Minimal token usage - No unnecessary resources loaded into context
• Mix and match - Compose multiple plugins for complex workflows
• Clear boundaries - Each plugin has a single, focused purpose
• Progressive disclosure - Skills load knowledge only when activated

Example: Installing python-development loads 3 Python agents, 1 scaffolding tool, and makes 16 skills available (~1000 tokens), not the entire marketplace.

Quick Start

Step 1: Install Qwen Code