ponytail-gain

Displays a benchmark scoreboard of ponytail's measured code, cost, and speed reductions.

166|78|Updated Aug 10, 2026
One-click install
npx skills add https://github.com/engasnm111/lnwjud --skill ponytail-gain-engasnm111
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-gain
Source: https://github.com/engasnm111/lnwjud/tree/main/.agents/skills/ponytail-gain
Command: npx skills add https://github.com/engasnm111/lnwjud --skill ponytail-gain-engasnm111

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users evaluating the ponytail approach lack a quick, honest summary of its measured impact, and risk seeing fabricated per-repo savings numbers that have no real baseline. ## Core Features & Use Cases - Benchmark Scoreboard: Renders a compact ASCII-bar scoreboard showing median reductions in lines of code (80–94%), cost (47–77%), and speed (3–6× faster) across 5 tasks and 3 models. - Honesty Boundary: Refuses to invent per-repo savings figures and instead points to /ponytail-debt and /ponytail-audit for real per-repo data. - One-Shot Display: Changes no mode, writes no files, and persists nothing; "stop ponytail" reverts. - Use Case: A developer asks "what does ponytail save" and immediately sees the published benchmark medians without any repo state being modified. ## Quick Start Ask the assistant to show the ponytail gain scoreboard to see the benchmark median savings for code, cost, and speed.

Frequently Asked Questions about ponytail-gain

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

FAQPage Schema
How do I see what ponytail saves on code and cost?▼

Invoke /ponytail-gain or ask "what does ponytail save" to render a compact ASCII scoreboard. It shows benchmark medians: 80–94% fewer lines of code, 47–77% lower cost, and 3–6× faster speed.

What benchmarks are the ponytail gain figures based on?▼

The figures are published benchmark medians from 5 everyday tasks (email validator, debounce, CSV sum, countdown timer, rate limiter) run across three models: Haiku, Sonnet, and Opus. They come from the benchmarks directory and README, not from your repository.

Can ponytail-gain show savings for my specific repository?▼

No, it deliberately refuses to print per-repo savings because the unbuilt baseline was never written, so no real subtraction is possible. For real per-repo figures it points you to /ponytail-debt and /ponytail-audit.

Does ponytail-gain change my mode or write any files?▼

No, it is a one-shot display that edits nothing, changes no mode, and writes no flag files. Saying "stop ponytail" or "normal mode" reverts to standard behavior.

When should I not rely on the ponytail gain scoreboard?▼

Do not treat the scoreboard as a measurement of your own codebase, since it reports benchmark medians only. Use it for a quick impact overview, then run /ponytail-debt or /ponytail-audit for counted, repo-specific data.