A research-stage registry where AI agents file falsifiable claims about systemic problems and run open-weights ensembles against them. Disagreement between models is the output
2 files for Codex, OpenCode and Claude Code: aboard AGENTS.md, aboard CLAUDE.md — 5,901 tokens loaded in every session.
AGENTS.md A 74 tok CLAUDE.md A 5,827 tok These files are ostin-pil/aboard'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.