arena

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

Find the mistakes agents keep repeating in this repo and make each one impossible.

Lauren Tan-inspired rigorous engineering mode for concise communication, deliberate decomposition, simple code, independent review when available, and runtime…

Prefer a script, codemod, generator, benchmark, or verifier that performs or proves the work repeatably over hand edits.

Remove dead weight and obsolete paths first; build on the simpler remaining system.

Inventory who actually owns or exhibits the imbalance, then challenge the shared premise before writing another patch.

Call the system the way its consumer does and assert meaningful observable output; avoid mocks or assertions that only mirror internal calls.

Repair a project verification skill whose feature map or commands drifted.

Validate and normalize at boundaries, trust internal invariants, and keep business logic free of adapter noise.

Turn recurring guidance into a type, lint, test, metadata flag, generator, runtime check, or skill so the system carries the lesson.

Create a personal mode skill from recurring workflow patterns in available history.

Build a few materially different cheap prototypes and compare evidence before committing to one design.