ponytail-gain

Displays benchmark median savings for lines of code, cost, and speed as an ASCII scoreboard.

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill ponytail-gain-chensihakniroth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-gain
Source: https://github.com/Chensihakniroth/ANAKOT-AGENT/tree/main/skills/ponytail/.openclaw/skills/ponytail-gain
Command: npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill ponytail-gain-chensihakniroth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It answers the question of what measured impact the ponytail approach delivers, showing published benchmark medians without inventing per-repo savings numbers. ## Core Features & Use Cases - Benchmark Scoreboard: Renders plain ASCII bars comparing no-skill versus ponytail results across lines of code, cost, and speed. - Honesty Boundary: Refuses to fabricate per-repo savings figures and instead points to /ponytail-debt and /ponytail-audit for real counted data. - One-Shot Display: Edits nothing, changes no mode, and persists no state; use it when you want a quick summary of measured benchmark outcomes from 5 tasks across 3 models. ## Quick Start Ask the agent to show the ponytail gain scoreboard to see the benchmark median impact on code size, 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 the measured impact of ponytail?▼

Invoke the ponytail-gain skill to render an ASCII scoreboard showing benchmark medians for lines of code, cost, and speed. The figures come from 5 everyday tasks run across Haiku, Sonnet, and Opus models.

What benchmark tasks does the ponytail scoreboard use?▼

The medians are measured from 5 everyday tasks: email validator, debounce, CSV sum, countdown timer, and rate limiter. Each task was run across three models, and the published medians are displayed as ASCII bars.

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

No, it deliberately avoids per-repo savings numbers because the unbuilt version of your repo was never written, so no real baseline exists. For real per-repo figures, use /ponytail-debt for a counted ledger or /ponytail-audit for what is still cuttable.

Does the ponytail-gain skill modify files or settings?▼

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 any related mode.

Why does the scoreboard show ranges instead of exact numbers?▼

The bars show measured ranges because results vary across the 5 benchmark tasks and 3 models. The labels carry the exact figures, such as 6-20% of original lines of code and 3-6x faster speed.