Is the Ponytail Audit skill free?

Yes. The skill itself is free from DietrichGebert/ponytail. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Ponytail Audit SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Ponytail Audit?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Ponytail Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Ponytail Audit

Whole-repo over-engineering audit: a ranked delete/simplify/replace list with net-line count

by DietrichGebert · DietrichGebert/ponytail

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 5582d10

Audited a 36-line over-engineered Python file both ways: the skill produced five ranked findings each naming the exact fix (s[::-1], sum(), dict.fromkeys(), json.load) with line ranges and a 'net: -28 lines' total, catching the O(n^2) dedupe and the never-read config flag. The no-skill baseline gave hedged prose with no line numbers, no replacement code, and no quantified payoff. For the stated goal of finding what to delete, the skill output is measurably more actionable.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Ponytail Audit does

Scans an entire codebase for over-engineering and returns a ranked, one-line-per-finding cut list tagged delete/stdlib/native/yagni/shrink, each naming the exact replacement, ending with a net-lines-removable metric. Triggers on 'audit this codebase', 'what can I delete', 'find bloat', or /ponytail-audit. One-shot report that applies nothing.

How to install Ponytail Audit

git clone https://github.com/DietrichGebert/ponytail
mkdir -p ~/.claude/skills
cd ponytail && cp -r skills/ponytail-audit ~/.claude/skills/

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Ponytail Audit

/ponytail-audit Whole-repo over-engineering audit: a ranked delete/simplify/replace list with net-line count

It also activates on plain-language prompts like these:

Audit this codebase and tell me what I can delete
Find the bloat in this repo and rank it by lines saved
What over-engineered code in here should I simplify or cut?

Frequently asked questions

Is the Ponytail Audit skill free?: Yes. The skill itself is free from DietrichGebert/ponytail. SkillProof publishes the install command and an independent test verdict at no cost.
Does Ponytail Audit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Audited a 36-line over-engineered Python file both ways: the skill produced five ranked findings each naming the exact fix (s[::-1], sum(), dict.fromkeys(), json.load) with line ranges and a 'net: -28 lines' total, catching the O(n^2) dedupe and the never-read config flag. The no-skill baseline gave hedged prose with no line numbers, no replacement code, and no quantified payoff. For the stated goal of finding what to delete, the skill output is measurably more actionable.
What is the Ponytail Audit SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Ponytail Audit?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Ponytail Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.