ponytail-audit

Audits an entire codebase for over-engineering and ranks deletable code, dependencies, and abstractions.

Updated May 26, 2026
One-click install
npx skills add https://github.com/avel123111/triplanio --skill ponytail-audit-avel123111
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ponytail-audit
Source: https://github.com/avel123111/triplanio/tree/main/.claude/skills/ponytail-audit
Command: npx skills add https://github.com/avel123111/triplanio --skill ponytail-audit-avel123111

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate dead code, redundant abstractions, and hand-rolled utilities that duplicate standard library or platform features. This Skill scans the whole repository and produces a ranked list of what to delete, simplify, or replace, so you can reduce maintenance burden without a manual line-by-line review. ## Core Features & Use Cases - Whole-repo over-engineering scan: Unlike a diff-based review, it audits the entire codebase tree and ranks findings biggest cut first. - Tagged findings: Each finding is labeled as delete (dead code), stdlib (hand-rolled standard library equivalents), native (platform-built-in replacements), yagni (speculative abstractions), or shrink (same logic in fewer lines). - Read-only report: It lists findings with file paths and an estimated net line/dependency reduction, but applies no changes itself. - Use Case: Before a major refactor, run the audit on a React/Vite/Supabase repo to find wrappers that only delegate, single-implementation interfaces, and dependencies the platform already provides. ## Quick Start Ask the AI to run ponytail-audit on this repository and list what can be deleted or replaced with standard library equivalents.

Frequently Asked Questions about ponytail-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit a codebase for over-engineering?

Run a whole-repo audit that scans every file for dead code, speculative abstractions, and hand-rolled utilities duplicating the standard library. Findings are tagged by type and ranked biggest cut first, with file paths for each item.

What is the difference between ponytail-audit and ponytail-review?

ponytail-audit scans the entire repository tree, while ponytail-review only examines a diff. Both use the same tagging system (delete, stdlib, native, yagni, shrink), but the audit suits periodic full-codebase cleanups rather than per-change review.

Does the over-engineering audit modify or delete code automatically?

No, the audit is read-only and one-shot. It lists findings with recommended replacements and an estimated net line and dependency reduction, but applies nothing. You decide what to act on.

What kinds of issues does a code bloat audit not catch?

Correctness bugs, security vulnerabilities, and performance problems are explicitly out of scope. Those should be routed to a normal code review pass; the audit only targets complexity and over-engineering.

When should I not run a whole-repo simplification audit?

Avoid it when you need feedback on a specific pull request or change set, since a diff-scoped review is more appropriate. It is also not a substitute for security or correctness review.