simplify

Simplify

Audit an existing implementation against its intended outcome. Prefer deleting over simplifying, simplifying over optimizing, and optimizing over automating. Preserve required behavior and prove the exact surface that changed. A valid result may be no_justified_edit when every candidate would add risk, ceremony, or scope.

When To Use

• The user explicitly asks to simplify an existing implementation or change.
• The user wants a first-principles simplification pass after implementation.
• The target has an existing diff, named file, or clearly edited scope.

Do not use for generic code review, net-new feature design, or broad architecture rewrites without an explicit simplification request.

Inputs

• The intended user outcome, required behavior, and assumptions behind the implementation.
• The intended comparison or merge base and the user-named scope.
• Staged, unstaged, and relevant untracked files, including dependencies that the patch references.
• Generated artifacts and the commands that own them, when applicable.
• Any focus area such as performance, helper reuse, JSX nesting, or error handling.
• Repository validation commands from local instructions.
• Dirty files that are unrelated or have uncertain ownership and must remain outside the edit boundary.
• The evidence source being treated as truth: local checkout, local branch, remote branch, or hosted PR diff.

When the request is underspecified, read references/discovery-interview.md and ask one plain-language question at a time. Explain why the answer changes the cleanup decision.

Outputs

For a small interactive cleanup, use four concise fields:

• Outcome: changed, no_justified_edit, or blocked.
• Evidence: the exact supplied diff or file fact supporting that outcome.
• Validation: the focused command or artifact required before claiming preserved behavior.
• Skipped / boundary: risky candidates left untouched and the remaining behavior boundary.

For validation removal, the Validation field must name both an accepted-input case and a rejected-input case, their expected results, and whether each ran.