lazy-clean

Use for coding tasks, bug fixes, refactors, code reviews, or requests for lazy mode, simpler code, or less over-engineering. Not for unrelated prose or general knowledge.

Whole-repo audit for over-engineering. Like lazy-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "find dead code", "which dependencies can we drop", "lazy-audit", or "/lazy-audit". One-shot report, does not apply fixes.

Write clean minimal code — the lazy ladder while writing, the slop-check checker after. Use when the user wants BOTH passes on one change, says "lazy-clean", asks for code that is lazy and slop-free, or wants over-engineering and AI slop caught together. For the ladder alone use lazy; for the checker alone use slop-check.

Harvest every `lazy:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals lazy leaves behind get tracked instead of rotting into "later means never". Use when the user says "lazy debt", "/lazy-debt", "what did lazy defer", "list the shortcuts", "lazy ledger", "tech debt ledger", or "what did we mark to do later". It tracks `lazy:` markers only, not generic TODOs. One-shot report, changes nothing.

Show Ponytail's upstream benchmark results and lazy-clean's own evaluation sources as a compact scoreboard. One-shot display, not a persistent mode or a per-repo savings estimate. Trigger: /lazy-gain, "lazy gain", "what does lazy save", "show lazy impact", "lazy scoreboard".

Quick-reference card for all lazy modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /lazy-help, "lazy help", "what lazy commands", "how do I use lazy".

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete from this diff", "is this over-engineered", "simplify review", or invokes /lazy-review. Complements correctness-focused review, this one only hunts complexity.

Explicitly requested, optional fix or preservation evidence through a separately reviewed local verification engine. Experimental; not a lazy intensity or automatic completion hook.

Detect and remove AI slop — pointless, low-evidence, or filler code — in TypeScript and JavaScript. Use after writing or editing TypeScript or JavaScript, when reviewing a diff or pull request, or whenever the user asks to check for slop, clean up AI-generated code, or run slop-check. Fully self-contained; runs with plain node and requires no npm packages or project configuration.