abhixz13/everything-claude-code — reverse-engineered prompt

Reverse engineered prompt

GitHub

Build me a complete open source toolkit that helps people get better results from AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Gemini.

I want it to feel like a practical performance system, not just a folder of prompts. It should include reusable agents, skills, rules, hooks, memory helpers, security checks, and setup files that can be installed into different coding assistants. A user should be able to run one installer, choose what parts they want, and then have their assistant remember project context, reuse good patterns, research docs before coding, verify its work, and avoid risky actions.

Please include clear docs, quick start guides, examples, a troubleshooting guide, and a simple local dashboard for viewing or managing the setup. Make it friendly for people who are not experts, but solid enough for daily software work. Also add tests or validation scripts so the system can check that the catalog, installs, and configs are working. Look up current docs online if you need to.

Want more depth? Deep Reverse