fuck-over-engineering

# Fuck Over-Engineering Audit the scope for over-engineering and report what to cut, ranked biggest cut first. The best outcome is a shorter codebase with the same behavior. The argument is the scope; without one, the whole tree. Read what the scope holds before judging it, and fan out subagents when it will not fit in context. ## Tags - `delete:` dead code, unused flexibility, speculative feature. Nothing replaces it. - `reuse:` hand-written code that a helper already in this codebase, or an installed dependency, already provides. Name the helper or function. - `stdlib:` hand-rolled thing the language's standard library ships. Name the function. - `native:` dependency or code doing what the platform already does. Name the feature. - `yagni:` abstraction with one implementation, config nobody sets, layer with one caller. - `shrink:` same logic, fewer lines. Show the shorter form. ## Hunt Dependencies the stdlib or platform already covers, single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib, near-duplicates of an existing helper, special-case branches bolted onto shared paths, feature logic living in shared modules. ## Evidence Every finding cites the evidence that makes it a cut: caller count, implementation count, or the stdlib or platform feature and the version that ships it. Count callers through dynamic dispatch, entry points, hooks, and tests, not grep alon...