Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/recca0120/code-quest/battle-managementnpx skills add recca0120/code-quest --skill battle-managementgit clone --depth 1 https://github.com/recca0120/code-questWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/recca0120/code-quest/battle-management)<a href="https://agentmods.dev/skills/recca0120/code-quest/battle-management"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/battle-management.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.04138 |
| Opus 5 | $0.00036 | $0.02069 |
| Sonnet 5 | $0.00014 | $0.00828 |
| Haiku 4.5 | $0.00007 | $0.00414 |
Grade A, and why
battle-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
戰鬥管理系統 - 多 AI 並行戰鬥設計（Roadmap，尚未實作）
⚠️ 本 skill 描述 Code Quest RPG 願景的戰鬥系統，目前 cc-office 未實作。當前專案是 Claude Code web client — 現況見
project-overview。
核心設計理念
Code Quest 採用 Dragon Quest (DQ) 風格 的戰鬥管理：
- 單一焦點：同一時間只顯示一場戰鬥（全螢幕）
- 選單驅動：使用彈出式選單切換戰鬥（非持續顯示的 Tab）
- 沉浸式體驗：保持傳統 RPG 的視覺純粹性
同時支援多 AI 並行：可以同時派遣 Haiku、Sonnet、Opus 三個 AI 代理處理不同任務。
混合方案：派遣 + 快速選單
設計決策
經過多方案比較，選擇了混合方案：
| 方案 | DQ純粹性 | 便利性 | 採用 |
|---|---|---|---|
| 純派遣系統 | ⭐⭐⭐⭐⭐ | ⭐⭐ | ❌ 太純粹，缺乏監控 |
| PIP子視窗 | ⭐ | ⭐⭐⭐⭐ | ❌ 破壞沉浸感 |
| Tab分頁系統 | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ❌ 持續顯示Tab列 |
| 混合方案 | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ✅ 平衡最佳 |
混合方案特點：
- ✅ 主要模式：背景派遣（不可見）
- ✅ 便利補充：DQ風格彈出選單（按需顯示）
- ✅ 完美平衡：保持沉浸感 + 提供監控能力
派遣系統 (6 步驟)
步驟 1：進入派遣介面
觸發方式：
- 城鎮「公會大廳」→「派遣任務」
- 野外遇到任務時選擇「派遣代理」
步驟 2：選擇 AI 代理
三種 AI 代理：
| 代理 | 特性 | MP消耗 | 適用場景 |
|---|---|---|---|
| Haiku 🌸 | 速度快、成本低 | 5 MP/回合 | 簡單任務、快速迭代、測試想法 |
| Sonnet 🎵 | 平衡、可靠 | 15 MP/回合 | 一般開發任務、程式碼重構 |
| Opus 👑 | 強大、深思熟慮 | 50 MP/回合 | 複雜架構、關鍵決策、棘手Bug |
選擇建議：
- 簡單 Bug 修復 → Haiku（快速、便宜）
- 功能開發 → Sonnet（平衡、可靠）
- 架構重構 → Opus（強大、深思）
步驟 3：選擇監控模式
三種監控模式：
| 模式 | 說明 | 適用情境 |
|---|---|---|
| 完全背景 🔇 | AI自主工作，只在需要決策時通知 | 簡單任務、信任AI能力 |
| 觀察模式 👁️ | 可透過快速選單查看進度，不主動通知 | 想掌握進度，但不想被打斷 |
| 即時監控 📺 | 切換到該戰鬥畫面，即時查看AI動作 | 學習、調試、關鍵任務 |
模式選擇建議：
- 高信任：完全背景（「交給AI，我去做其他事」）
- 中等信任：觀察模式（「我想知道進度，但不想一直盯著」）
- 學習/調試：即時監控（「我想看AI怎麼做」）
步驟 4：選擇工作環境
兩種環境選項：
| 環境 | 視覺標示 | 說明 | 適用情境 |
|---|---|---|---|
| 當前目錄 | 🔵 藍色 | 直接在專案目錄工作 | 小型修改、測試 |
| Worktree 隔離 | 🟣 紫色 | 建立獨立工作樹，完全隔離 | 大型重構、實驗性功能 |
設計理由：
- 視覺區分：顏色讓你一眼看出戰鬥的隔離狀態
- 風險提示：當前目錄會提示風險，引導複雜任務使用Worktree
- 自動建議：系統根據任務複雜度自動推薦環境
步驟 5：自動戰鬥設定
AI 可自動處理：
- ✅ 選擇工具（Read, Write, Grep等）
- ✅ 讀取檔案
- ✅ 編輯程式碼
- ✅ 執行測試
- ✅ 簡單git操作（add, commit）
需要玩家決策：
- ❌ git push（影響遠端）
- ❌ 刪除檔案（不可逆）
- ❌ 安裝新套件（改變依賴）
- ❌ 修改設定檔（影響專案）
- ❌ 遇到複雜錯誤（需要策略）
平衡點：
- 90% 操作自動化（便利）
- 10% 關鍵操作需確認（安全）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 375 lines · 71 tokens per session scan A 036c78abba5f
battle-management is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 4,138 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.