CXPhoenix/everything-claude-code ? reverse-engineered prompt
Reverse engineered prompt
Build me a repo that acts like a complete starter kit for Claude Code and other AI coding agents, with the same kind of agents, skills, hooks, rules, commands, and MCP setup described in the README. I want it to work across Claude Code, Cursor, Codex, Gemini, and OpenCode, and make it easy to install only the pieces I need instead of everything at once.
Please include clear docs, setup scripts for Mac and Windows, example configs, and a simple way to keep track of what is installed. It should feel polished and production ready, with sensible defaults for memory, research first workflows, security checks, and session context reuse. If there are any current docs or best practices that would help, look them up online and use them. Also make sure the repo is organized so it is easy for someone to browse, understand, and plug into their own agent workflow without needing to be an expert.
Are you gonna build this?
make sure you review the code using coderabbit