Skip to content

micln/agent-init

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

agent-init

Initialize AI coding environments for your projects.

📖 中文文档

Why

Setting up AI coding agents from scratch means manually choosing MCP servers, skills, and configuration files for each project. agent-init automates this: detect your stack, pick the right tools, and generate ready-to-use config -- so you can skip the boilerplate and start coding.

What it does

agent-init is a skill that detects your project and configures an optimal environment for AI coding agents. When invoked, it:

  1. Detects your project type (language, framework, build tools)
  2. Recommends MCP servers and skills matched to your stack
  3. Generates configuration files (.mcp.json, AGENTS.md)
  4. Optionally suggests heavy tools (CodeGraph, RTK, Superpowers) for you to approve

Quick Start

Install the init-harness skill with npx skills:

npx skills add micln/agent-init

Claude Code

After install, run it in Claude:

/init-harness

OpenCode

After install, reference init-harness in your OpenCode config and invoke it.

Supported Project Types

Type Profile Key MCP Servers
Generic base.md context7, github
Next.js nextjs.md context7, github, next-devtools, playwright
React react.md context7, github, playwright
Godot godot.md context7, github, godot-mcp
Go go.md context7, github

Heavy Tools (Optional)

These are high-impact developer tools that require user confirmation before installation:

Tool Purpose Install
CodeGraph Code knowledge graph (59K stars) npx @colbymchenry/codegraph
RTK Token compression (70K stars) cargo install --git https://github.com/rtk-ai/rtk
Superpowers Development methodology (253K stars) See docs

License

MIT

About

init project configs for ai coding

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors