Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
2 files for Codex, OpenCode and Claude Code: chi-bench AGENTS.md, chi-bench CLAUDE.md — 5,110 tokens loaded in every session.
AGENTS.md A 4 tok CLAUDE.md A 5,106 tok These files are actava-ai/chi-bench's own configuration — they tell 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.