Cookbooks
Each cookbook is one task: the prompt to paste into your coding agent, and rb’s output from running it.
Record where the work stands from the repository’s own files, with no questions asked first.
Record one table of many runsEach row of results.tsv is a run, recorded with one command per arm.
Record a folder per runEach run’s own folder, recorded from what its config says.
Check a summary's claims against the runsTurn each claim in an agent’s summary into a criterion: a rule rb checks against the runs.
Declare the criterion before the runsDeclare what counts and freeze it, so rb shows it came first.
Compare against a published baselineCite the paper’s number and settings. rb says reproduced or not reproduced.
Get an interval, not a single numberRun seeds until the criterion has the interval it needs.
Read a rule over seedsRules over the seeds, such as a count or a best of N.
Share the record, and rerun itA page your advisor reads, and a bundle their agent clones and reruns.
Rerun a run from its receiptA run’s receipt says what ran and on which commit. Rerun it on that commit as a check.
rb with Claude Code, Codex and CursorOne record, whichever agent writes to it.
About the output on these pages
Section titled “About the output on these pages”Every output block is real, from rb 0.8.4. Each cookbook ran on a small project whose script writes fixed numbers per seed. Commands marked as yours ran in a plain terminal, the rest in an agent session as Claude Code runs them. After the runs, we replaced the folder’s path with ~ and cut long outputs where a line says so.
Ids such as run4k2xa9, hashes and times differ in your run.
Rabbit Brainrabbitbrain.ai · GitHub · PyPI · Privacy · Apache-2.0