Instructions file CodexOpenCode
AGENTS.md instructions for 263311487-ux/falsify, covering agents.md — falsify and if an agent is working in this repo.
0 3d ago A 280 tokens
original MIT
The scientific thinking protocol for AI agents — falsify before you believe. 5-stage falsification skill (axioms → hypothesis → adversarial → verify → converge) for Codex, Claude Code, Cursor, Gemini CLI & 20+ agents. Dual-model evals 26/28. 五段式科学思维协议:公理 → 假设 → 对抗 → 验证 → 收束。
Instructions file CodexOpenCode
AGENTS.md instructions for 263311487-ux/falsify, covering agents.md — falsify and if an agent is working in this repo.