affaan-m/ecc — reverse-engineered prompt
Reverse engineered prompt
Build me an open source toolkit that helps AI coding agents work better across Claude Code, Codex, Cursor, OpenCode, Gemini, Zed, and Copilot.
I want it to feel like a practical operator system for agentic coding work, not just a pile of config files. It should include reusable agent profiles, skills, rules, hooks, memory helpers, command shims, and MCP configs that people can install into their favorite coding tool. The goal is to make agents remember useful project context, learn patterns from past sessions, research before changing code, run safer workflows, and catch security issues before they become problems.
Please include a simple installer, clear docs, examples, a quick reference for commands, and a small desktop dashboard where I can see available agents, skills, status, and basic settings like theme and font size. Keep it friendly for solo developers, but structured enough for real production repos. Look up current docs online if you need to.
Want more depth? Deep Reverse