What problem does it solve? Codebases accumulate dead code, speculative abstractions, redundant dependencies, and hand-rolled utilities that the standard library already provides. Manually finding this bloat across a whole repository is slow and inconsistent, and teams often lack a structured way to decide what to cut first. ## Core Features & Use Cases - Whole-Repo Over-Engineering Scan: Scans the entire codebase rather than a diff, hunting for dead code, single-implementation interfaces, one-product factories, delegating wrappers, unused config flags, and hand-rolled stdlib equivalents. - Tagged, Ranked Findings: Classifies each finding as delete, stdlib, native, yagni, or shrink, and ranks them biggest cut first with a concrete replacement suggestion and file path. - Net Impact Summary: Ends the report with an estimate of removable lines and dependencies, e.g. "net: -300 lines, -2 deps possible." - Use Case: Before a refactor sprint, ask for an audit of your repository to get a prioritized list of what to delete, what to replace with standard library functions, and which abstractions to collapse. ## Quick Start Ask the AI to audit this codebase for over-engineering and list what can be deleted or replaced with stdlib equivalents.
