Standardize benchmark wrapping so the community can wrap various otherwise-incompatible benchmarks uniformly and use them everywhere.
These files are The-AI-Alliance/cube-standard's own configuration. They tell Claude Code, Codex and OpenCode 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.
AGENTS.md A 4 tok CLAUDE.md A 2,553 tok .claude/skills/gatekeep-rfc/SKILL.md A 121 tok .claude/skills/new-cube/SKILL.md A 64 tok .claude/skills/review-cube/SKILL.md A 92 tok .claude/commands/update-openspec.md A —