Rigorous Proofs via Adversarial AI Agents
13 files for Claude Code, Codex and OpenCode: add-node, cancel-ralph, edn-to-lean, extract-lemma and 9 more — 444 tokens loaded in every session.
AGENTS.md A 444 tok .claude/commands/add-node.md A 8 tok .claude/commands/cancel-ralph.md A — .claude/commands/edn-to-lean.md A 10 tok .claude/commands/extract-lemma.md A 7 tok .claude/commands/fix-sorries.md A 10 tok .claude/commands/init-graph.md A 6 tok .claude/commands/ralph-loop.md A — .claude/commands/stats.md A 3 tok .claude/commands/status.md A 13 tok .claude/commands/update-status.md A 8 tok .claude/commands/validate-graph.md A 13 tok .claude/commands/verify-proof.md A 13 tok These files are tobiasosborne/alethfeld'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.