piecioshka/whose-context-wins

Poligon do sprawdzania, który plik konfiguracyjny (CLAUDE.md, AGENTS.md, .cursorrules...) realnie czyta dany agent AI — z automatycznym pomiarem przez CLI

5 files for Cursor, GitHub Copilot, Codex, OpenCode and Claude Code: cursorrules, whose-context-wins copilot-instructions.md, whose-context-wins kolor.instructions.md, whose-context-wins AGENTS.md and 1 more — 62 tokens loaded in every session.

Open on GitHub

Instructions

whose-context-wins copilot-instructions.md .github/copilot-instructions.md A 11 tok
whose-context-wins kolor.instructions.md .github/instructions/kolor.instructions.md A 18 tok
whose-context-wins AGENTS.md AGENTS.md A 13 tok
whose-context-wins CLAUDE.md CLAUDE.md A 10 tok

Cursor rules

cursorrules .cursorrules A 10 tok

These files are piecioshka/whose-context-wins's own configuration — they tell Cursor, GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.