ponytail-gain
顯示 ponytail 在 benchmark 量到的程式碼、成本、速度節省幅度
中文翻譯
---
name: ponytail-gain
description: >
顯示 ponytail 在 benchmark 中量測到的節省幅度（程式碼、成本、速度）。
一次性顯示。用於 /ponytail-gain、「what does ponytail save」、
「ponytail impact」。
---
# Ponytail Gain
被呼叫時，顯示這張計分板。一次性：**不要**改模式、寫旗標
檔案，或保存任何東西。
這些數字來自 Ponytail 5 公開的 agentic benchmark：無頭模式的 Claude
Code（Opus 5.5，預設 effort），跑 39 個任務（真實 FastAPI +
React repo 裡的功能 ticket、bug 修復、安全與隱私案例、小型 app），每個跑 5 次，
對照沒有這個 skill 的同一個 agent。其中 18 個任務有隱藏的檢查，
驗證正確性和安全性。每個數字是各任務中位數的幾何平均。
它們是量測出來的，不是從目前的 repo 算出來的。
來源：`benchmarks/results/2026-10-07-agentic.md` 和 README。
## 計分板
用純 ASCII 畫長條。長條長度表示 ponytail 佔
沒有 skill 基準線的比例；標籤帶有精確的數字：
```
ponytail gain benchmark · 39 tasks × 5 runs · Opus 5.5
no-skill ████████████████████ 100%
Lines of code █████████··········· 47% ▼ 53%
Output tokens ███████████········· 55% ▼ 45%
Cost ███████████████····· 74% ▼ 26%
Time ████████████········ 59% ▼ 41%
Hidden checks passed 97% (no-skill 96%)
Tests where the logic needs one 98% (no-skill 68%)
This repo: /ponytail-debt (shortcuts you deferred)
/ponytail-audit (what's still cuttable)
```
## 誠實的界線
這些是 benchmark 的平均值，不是這個 repo 的數字。**絕對不要**印出針對單一 repo 的節省
數字（「你在這裡省了 X 行/token」）：沒蓋出來的那個版本從來沒寫過，
所以在真實的 repo 裡，沒有真正的基準線可以拿來相減。
唯一真正針對單一 repo 的數字，來自 `/ponytail-debt`（有計數的帳本），
而這張卡片是指向那裡，不是自己編一個。
## 範圍界線
一次性顯示。不編輯任何東西，不改任何模式。英文原文
---
name: ponytail-gain
description: >
Show ponytail's measured savings (code, cost, speed) from the benchmark.
One-shot display. Use for /ponytail-gain, "what does ponytail save",
"ponytail impact".
---
# Ponytail Gain
Display this scoreboard when invoked. One-shot: do NOT change mode, write flag
files, or persist anything.
The figures are the published agentic benchmark of Ponytail 5: headless Claude
Code (Opus 5.5, default effort) on 39 tasks (feature tickets in a real FastAPI +
React repo, bug fixes, security and privacy cases, small apps), 5 runs each,
against the same agent without the skill. 18 of the tasks have hidden checks
for correctness and safety. Each figure is the geometric mean of the per-task
medians. They are measured, not computed from the current repo.
Source: `benchmarks/results/2026-10-07-agentic.md` and the README.
## Scoreboard
Render plain ASCII bars. The bar length shows ponytail as a share of the
no-skill baseline; the label carries the exact figure:
```
ponytail gain benchmark · 39 tasks × 5 runs · Opus 5.5
no-skill ████████████████████ 100%
Lines of code █████████··········· 47% ▼ 53%
Output tokens ███████████········· 55% ▼ 45%
Cost ███████████████····· 74% ▼ 26%
Time ████████████········ 59% ▼ 41%
Hidden checks passed 97% (no-skill 96%)
Tests where the logic needs one 98% (no-skill 68%)
This repo: /ponytail-debt (shortcuts you deferred)
/ponytail-audit (what's still cuttable)
```
## Honesty boundary
These are benchmark averages, not this repo. NEVER print a per-repo savings
number ("you saved X lines/tokens here"): the unbuilt version was never
written, so there is no real baseline to subtract from in a live repo. The
only real per-repo figures come from `/ponytail-debt` (a counted ledger), and
this card points there instead of inventing one.
## Boundaries
One-shot display. Edits nothing, changes no mode.