Use when modifying code without tests — characterization tests pin current behavior as a golden baseline, find seams for safe injection, and keep edits minimal and localized.

Maintain a persistent scratchpad file (progress log, open questions, decisions, current failing command) during long work so nothing is lost. Use for any task spanning many steps.

Trust but verify a subagent/agent's "done" claim — run the tests, read the diff, check the artifacts actually exist. Use before accepting any delegated or automated result.

Adopt strict static typing in Python — full annotations, no Any, mypy/pyright in strict mode, and gradual migration. Use when a Python codebase is growing and needs type safety.

Use when writing new code — the RED-GREEN-REFACTOR loop: write a failing test first, minimal code to pass, then refactor. Never write production code without a failing test.

Decompose a feature or bug into an ordered list of small, independently testable subtasks before writing any code. Use when a task feels too big to start or keeps sprawling.

Use when debugging any bug — 4-phase root cause methodology: reproduce, isolate, hypothesize, fix-verify. No code changes before a repro exists.

Decide when to delegate to a subagent, write a scoped self-contained brief, and hand off cleanly. Use when a task is independent enough to run in parallel or in isolation.

Diagnose slow SQL with EXPLAIN, identify the real cause (missing index, N+1, full scan), and fix it. Use for any slow database query.

Run a timeboxed throwaway experiment to de-risk an unknown (a library, an API, a perf question) before committing to an architecture. Use when you don't know whether an approach will work.