---
title: "coach"
url: "https://claudemods.dev/zh-tw/builds/coach-d18572"
source: "https://github.com/eshin087/claude-code-mods/tree/main/coach"
source_type: "github"
repo: "https://github.com/eshin087/claude-code-mods/tree/main/coach"
author: "eshin087"
author_handle: "eshin087"
stars: 0
category: "其他"
categories: ["other"]
tags: []
permission_level: 2
scan_complete: true
install: "claude plugin marketplace add eshin087/claude-code-mods\nclaude plugin install coach"
added: "2026-10-05T01:57:25.163Z"
updated: "2026-10-25T21:14:22Z"
locale: "zh-tw"
content_locale: "zh-tw"
---

# coach

/coach：即時成本、快取、上下文和子代理程式統計、SDLC 習慣檢查和架構師課程；關鍵時刻，轉彎後給出提示。

## Description

# 教練

**它的作用：** 顯示您的會話背後推動成本和品質的數字，根據正常軟體生命週期 (SDLC) 檢查您的習慣，並一次教授一個與您剛剛所做的事情相關的 architect-level 概念。目的是將vibe-coding技能運用到實際的工程工作中。

**您在哪裡看到它：**
- 擴充座（或 `/coach`）中的 **C** 切換面板：
```
  ● Cache    92%   ━━━━━━━━━━━  reusing context well
  ● Context  41%   ━━━━━━━━━━━  room to spare
  ● Cost     $3.20             $0.27 per turn
  Habits   ✓ Plan  ✓ Branch  ✗ Tests  ✓ Commits  · PR
  Do next  Run the tests: 8 edits since the last run
  Tokens   120k fresh  4.1M cached  300k cache-write  52k out
  Model    claude-opus-5-5  effort high  subagents 4 runs · 31% of tokens
  Lesson   The test pyramid
           Many fast unit tests at the base, fewer integration tests…
  
```-
 **顏色：** 綠色表示良好，黃色表示觀看，紅色表示行動。在權杖行中，快取的權杖為綠色（便宜），cache-writes 為黃色，輸出為青色。
  - **更多**添加了課程的“下一步嘗試”和“工作中”註釋（帶有**另一節課**）和 Claude Code 專業提示（帶有**下一步提示**和連結）。
- **將 C** 懸停在擴充座中，查看紫羅蘭卡，其中包含快取和上下文欄、成本、習慣和「下一步」。
- **一輪後一個提示，僅當規則觸發時**，作為聊天中暗淡的 `🎓 Coach · …` 行：
  - 直接致力於主要
  - 在大轉彎時 50% 下的緩存命中（可能的原因）
  - 75% 完整上下文
  - 自上次執行測試以來 5+ 編輯
  - 一輪費用超過~$2
  - 10+ 沒有計劃的建築分鐘數
  - 代理程式使用超過一半的代幣

  相同的刀尖在重複之前至少等待 6 圈。

**術語表：**
- **提示快取：**應用程式每次都會 re-sends 整個對話。快取命中意味著前綴被重複使用，並按新輸入的 ~10% 計費。模型切換、CLAUDE.md 或記憶體編輯、/compact 或空閒間隙（快取過期）上的命中斷。
- **上下文填入：**對話使用模型視窗的多寡。富勒意味著速度更慢、價格更高、品質接近極限。
- **成本：** API 價格。在訂閱中，這是您使用的價值，而不是帳單，但它會追蹤您燃燒 5-hour 視窗的速度。

**它是如何運作的：**一切都來自應用程式已經報告的內容（每回合的權杖使用情況、會話成本和上下文、編輯、測試、提交和 `gh pr create` 等工具呼叫）。沒有模型呼叫。

**成本：**無。

**已儲存的資料：**磁碟上沒有資料。會議統計資料即時顯示。

## Install

```
claude plugin marketplace add eshin087/claude-code-mods
claude plugin install coach
```

## Original README

# Coach

**What it does:** shows the numbers behind your sessions that drive cost and quality, checks your habits against a normal software lifecycle (SDLC), and teaches one architect-level concept at a time, tied to what you just did. The aim is to carry vibe-coding skill into real engineering work.

**Where you see it:**
- **C** in the dock (or `/coach`) toggles the panel:
  ```
  ● Cache    92%   ━━━━━━━━━━━  reusing context well
  ● Context  41%   ━━━━━━━━━━━  room to spare
  ● Cost     $3.20             $0.27 per turn
  Habits   ✓ Plan  ✓ Branch  ✗ Tests  ✓ Commits  · PR
  Do next  Run the tests: 8 edits since the last run
  Tokens   120k fresh  4.1M cached  300k cache-write  52k out
  Model    claude-opus-5-5  effort high  subagents 4 runs · 31% of tokens
  Lesson   The test pyramid
           Many fast unit tests at the base, fewer integration tests…
  ```
  - **Colors:** green is good, yellow means watch it, red means act. In the token row, cached tokens are green (cheap), cache-writes yellow and output cyan.
  - **More** adds the lesson's "try next" and "at work" notes (with **Another lesson**) and a Claude Code pro tip (with **Next tip** and links).
- **Hover C** in the dock for a violet card with the cache and context bars, cost, habits and "do next".
- **One tip after a turn, only when a rule fires,** as a dim `🎓 Coach · …` row in the chat:
  - committed straight to main
  - cache hit under 50% on a big turn (with the likely cause)
  - context over 75% full
  - 5+ edits since tests last ran
  - a turn costing over ~$2
  - 10+ minutes of building with no plan
  - subagents using over half the tokens

  The same tip waits at least 6 turns before repeating.

**Glossary:**
- **Prompt cache:** the app re-sends the whole conversation every turn. A cache hit means that prefix was reused and billed at ~10% of fresh input. Hits break on model switches, CLAUDE.md or memory edits, /compact, or idle gaps (the cache expires).
- **Context fill:** how much of the model's window the conversation uses. Fuller means slower, pricier, and lower quality near the limit.
- **Cost:** API prices. On a subscription this is the value you used, not a bill, but it tracks how fast you burn your 5-hour window.

**How it works:** everything comes from what the app already reports (token usage per turn, session cost and context, tool calls such as edits, tests, commits and `gh pr create`). No model calls.

**Cost:** none.

**Data saved:** none on disk. Stats live for the session.
