ponytail-audit

Audits an entire codebase for over-engineering and ranks findings to delete or simplify.

Updated May 8, 2026
One-click install
npx skills add https://github.com/tomw200082-collab/gt-factory-os-production-brain --skill ponytail-audit-tomw200082-collab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-audit
Source: https://github.com/tomw200082-collab/gt-factory-os-production-brain/tree/main/.claude/skills/ponytail-audit
Command: npx skills add https://github.com/tomw200082-collab/gt-factory-os-production-brain --skill ponytail-audit-tomw200082-collab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate dead code, speculative abstractions, and hand-rolled utilities that duplicate the standard library. This Skill scans the whole repository and produces a ranked list of what to delete, simplify, or replace with stdlib or native equivalents. ## Core Features & Use Cases - Whole-repo over-engineering audit: Scans the entire tree instead of a diff and ranks findings biggest cut first. - Tagged findings: Classifies each finding as delete, stdlib, native, yagni, or shrink, with a concrete replacement named. - Net impact summary: Ends with an estimate of lines and dependencies removable, or reports the codebase is already lean. - Use Case: Before a major refactor, run the audit to find single-implementation interfaces, one-product factories, dead config flags, and dependencies the platform already provides. ## Quick Start Ask the assistant to audit this codebase for over-engineering and list what can be deleted or replaced with stdlib 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 the full tree and ranks findings biggest cut first. Each finding is tagged as delete, stdlib, native, yagni, or shrink, with a concrete replacement named for each item.

How to find dead code and unused abstractions in a repository?▼

Hunt for single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, and dead flags or config. These patterns indicate speculative flexibility that can be removed.

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

ponytail-audit scans the entire repository instead of a diff, while ponytail-review focuses on changes. Both use the same tagging system for delete, stdlib, native, yagni, and shrink findings.

Does the over-engineering audit fix the issues it finds?▼

No, it is a one-shot report that lists findings and applies nothing. It produces a ranked list with a net line and dependency reduction estimate, leaving all changes to the user.

What issues are out of scope for a code bloat audit?▼

Correctness bugs, security holes, and performance problems are explicitly out of scope. The audit covers only over-engineering and complexity, routing other concerns to a normal review pass.