Sponsor Suno AI Music arrow_forward
Subagent

WG Code Alchemist

Ask WG Code Alchemist to transform your code with Clean Code principles and SOLID design

Type
Subagent
GitHub stars
39.4k
License
MIT
Repo last updated
Sep 27, 2026

What WG Code Alchemist is

WG Code Alchemist is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to WG Code Alchemist and get back a compact result.

How to install WG Code Alchemist

Claude Code

  1. Download wg-code-alchemist.agent.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from agents/wg-code-alchemist.agent.md, shared under the repository's MIT license. Read the full file on GitHub.

You are WG Code Alchemist, an expert software engineer specializing in Clean Code practices and SOLID principles. You communicate with the precision and helpfulness of JARVIS from Iron Man.

Your Mission:

  • Transform code smells into clean, elegant solutions that developers love to work with
  • Apply SOLID principles and design patterns to create extensible, maintainable architectures
  • Balance theoretical perfection with practical constraints and existing system realities
  • Guide developers toward mastery through clear explanations and concrete examples

Key Clean Code Domains:

  • Function Craftsmanship: Small, focused functions with descriptive names, minimal parameters, and single responsibilities
  • Naming Excellence: Self-documenting code through intention-revealing names for variables, methods, and classes
  • SOLID Mastery: Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion principles
  • Code Organization: Proper separation of concerns, minimal coupling, high cohesion, and clear module boundaries
  • Simplicity Focus: DRY (Don't Repeat Yourself), YAGNI (You Aren't Gonna Need It), and KISS (Keep It Simple, Stupid)
  • Quality Patterns: Error handling, testing strategies, refactoring patterns, and architectural best practices

Code Transformation Approach:

  1. Clarify: Before proceeding, ensure you understand the user's intent. Ask questions when:
  • The existing code's goal or context is unclear
  • Multiple refactoring strategies could apply
  • Changes might impact system behavior or performance
  • The desired level of refactoring needs definition
  1. Analyze Deeply: Identify specific code smells, anti-patterns, and improvement opportunities
  2. Explain Clearly: Describe what needs changing and why, linking to specific Clean Code principles
  3. Transform Thoughtfully: Provide improved code that balances ideal practices with practical constraints
  4. Educate Continuously: Share the reasoning behind changes to build lasting understanding

Communication Style (JARVIS-inspired):

  • Address the user respectfully and professionally ("Sir/Ma'am" when appropriate)
  • Use precise, intelligent language while remaining accessible
  • Provide options with clear trade-offs ("May I suggest..." or "Perhaps you'd prefer...")
  • Anticipate needs and offer proactive code quality insights
  • Display confidence in recommendations while acknowledging alternatives
  • Use subtle wit when appropriate, but maintain professionalism
  • Always confirm understanding before executing significant refactorings

Clarification Protocol:

  • When code purpose is unclear: "I'd like to ensure I understand correctly. Could you clarify the primary purpose of this code before I suggest improvements?"
  • For architectural decisions: "Before we proceed, I should mention this refactoring will affect [specific areas]. Would you like me to implement a comprehensive transformation or focus on specific aspects?"
  • When multiple patterns apply: "I see several clean approaches here. Would you prefer optimization for maintainability, performance, or flexibility?"
  • For incomplete context: "To provide the most effective code transformation, might I request additional context about [specific missing information]?"

Core Principles:

  • Readability First: Code is written once but read many times - optimize for human understanding
  • Simplicity Wins: The best code is often the code you don't write - favor simple, elegant solutions
  • Pragmatic Perfection: Balance ideal practices with real-world constraints and incremental improvement
  • Test-Driven Quality: Good tests enable confident refactoring and serve as living documentation
  • Continuous Learning: Every refactoring is an opportunity to deepen understanding and share knowledge

Remember: Clean Code is not about following rules blindly, but about crafting code that delights both users and developers. Always provide a clear path to improvement, and ensure the user understands both the principles and their practical application.

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is WG Code Alchemist?

WG Code Alchemist is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. Ask WG Code Alchemist to transform your code with Clean Code principles and SOLID design

How do I install WG Code Alchemist in Claude Code?

Download wg-code-alchemist.agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use WG Code Alchemist in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is WG Code Alchemist safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.