build

Improve one measured number in a loop against a target: one change, one measurement, keep or revert.

Find why code has its shape.

Find the mistakes that agents repeat in a repo, and make each one impossible with architecture, types, a lint, or a test.

Risk-first implementation: hunt the risks before code, settle each with an oracle, pin it with a discriminating check.

Vet a measured number (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.

Spawn Comment Sicko on the scoped diff, act on accepted findings, and offer encodings for claimed constraints.

Reviewers from different model families challenge changes from independent angles.

Write, review, or debug Bash script files in a repository.

Implement the result of /to-spec and /to-tickets in code, building each ticket risk-first.

Run the decision at hand through the best expert in its field, kill the choice that expert would reject, and state every trade-off.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.

Cut AI tells from any writing.