legacy-code-safetylisted

# Legacy Code Safety Make one requested change safe without demanding a cleanup campaign or rewrite first. Legacy code is code for which the relevant behavior cannot be verified quickly and reliably. Existing tests may be absent, slow, flaky, too broad, or coupled to irrelevant structure. The immediate job is to establish enough trustworthy feedback for the change at hand. ## Ownership and boundaries Use this skill when: - relevant behavior is undocumented, surprising, or poorly understood - existing tests do not protect the intended change - dependencies or side effects keep code out of a test harness - the task calls for characterization, pinning, approval tests, seams, sensing, separation, or safe legacy-code change - a large brownfield transformation needs an incremental path through live code Do not use it as the primary skill when: - a fast trustworthy test boundary already exists; use `unit-testing` - the request is review-only; use `representation-refactor-review` - the task is only to choose delivery slices; use `story-splitting-for-delivery` - the user requested a wholesale replacement; do not silently turn this skill into authorization for one This skill owns **establishing safety**. `unit-testing` owns specifying and implementing the new behavior after that boundary exists. ## Safety invariants - Start from an intentional workspace and record relevant inherited failures before editing. - Characterization describes observed behavior, not desired behavior.