
Agents change code faster than anyone rereads the docs. A 40-line Vitest file turns every TypeScript example in a README into a test, so stale docs fail the build. Fifteen minutes to set up.

A strictness ladder for a JS-to-TS migration that an agent can climb in small batches without changing behaviour by accident. About 20 minutes to try on one module.

A contract-first loop for a C# API and a TypeScript client: generated types for the client, a schema check on every response, and a failing test as the agent's brief. About 30 minutes, works with any agent.

A PostToolUse hook with asyncRewake runs your suite after each edit without blocking the agent, stays silent on a pass and wakes Claude Code with a trimmed failure report on a fail. Fifteen minutes to set up.

Tell an agent a test is flaky and it will add a retry. This setup makes it measure the failure rate, replay a failing seed and prove the fix, and it blocks the commit if the 'fix' is a retry, a sleep or a skip. About 15 minutes to try.

A recorder, a generated test file and a mutation run give you a safety net you can measure, not just feel good about. About 20 minutes to set up.