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/pixel-cellar/claude-code-game-studios/team-combatnpx skills add pixel-cellar/Claude-Code-Game-Studios --skill team-combatgit clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-StudiosWrote 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/pixel-cellar/claude-code-game-studios/team-combat)<a href="https://agentmods.dev/skills/pixel-cellar/claude-code-game-studios/team-combat"><img src="https://agentmods.dev/badge/skills/pixel-cellar/claude-code-game-studios/team-combat.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 5.1 | $0.00049 | $0.01011 |
| Opus 5 | $0.00024 | $0.00505 |
| Sonnet 5 | $0.00010 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
team-combat 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 2d 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.
What it actually says
当此技能被调用时，通过结构化流水线编排战斗团队。
决策点： 在每个阶段转换时，使用 AskUserQuestion 将子代理的方案作为可选项呈现给用户。在对话中展示代理的完整分析，然后用简洁的标签记录决策。用户批准后方可进入下一阶段。
团队组成
- game-designer（游戏设计师） — 设计机制，定义公式和边缘情况（Edge Case）
- gameplay-programmer（玩法程序员） — 实现核心玩法代码
- ai-programmer（AI 程序员） — 实现与该功能相关的 NPC/敌人 AI 行为
- technical-artist（技术美术） — 创建 VFX（视觉效果）、着色器（Shader）效果和视觉反馈
- sound-designer（音效设计师） — 定义音频事件、打击音效和环境战斗音频
- qa-tester（QA 测试员） — 编写测试用例并验证实现
如何委派
使用 Task 工具将每位团队成员生成为子代理：
subagent_type: game-designer— 设计机制，定义公式和边缘情况subagent_type: gameplay-programmer— 实现核心玩法代码subagent_type: ai-programmer— 实现 NPC/敌人 AI 行为subagent_type: technical-artist— 创建 VFX、着色器效果、视觉反馈subagent_type: sound-designer— 定义音频事件、打击音效、环境音频subagent_type: qa-tester— 编写测试用例并验证实现
始终在每个代理的提示中提供完整上下文（设计文档路径、相关代码文件、约束条件）。在流水线允许的情况下并行启动独立代理（例如，阶段 3 的代理可以同时运行）。
流水线
阶段 1：设计
委派给 game-designer：
- 在
design/gdd/中创建或更新设计文档，涵盖：机制概述、玩家幻想、详细规则、含变量定义的公式、边缘情况、依赖项、含安全范围的调优旋钮（Tuning Knob）以及验收标准（Acceptance Criteria） - 输出：完成的设计文档
阶段 2：架构设计
委派给 gameplay-programmer（如涉及 AI，同时委派 ai-programmer）：
- 审查设计文档
- 设计代码架构：类结构、接口、数据流
- 识别与现有系统的集成点
- 输出：架构草图，含文件列表和接口定义
阶段 3：实现（尽可能并行）
并行委派：
- gameplay-programmer：实现核心战斗机制代码
- ai-programmer：实现 AI 行为（如果功能涉及 NPC 反应）
- technical-artist：创建 VFX 和着色器效果
- sound-designer：定义音频事件列表和混音说明
阶段 4：集成
- 连接玩法代码、AI、VFX 和音频
- 确保所有调优旋钮已暴露且数据驱动
- 验证功能与现有战斗系统的兼容性
阶段 5：验证
委派给 qa-tester：
- 根据验收标准编写测试用例
- 测试设计文档中记录的所有边缘情况
- 验证性能影响在预算范围内
- 为发现的问题提交缺陷报告（Bug Report）
阶段 6：签收
- 收集所有团队成员的结果
- 报告功能状态：完成 / 需要修改 / 阻塞
- 列出所有未解决问题及其负责人
输出
一份总结报告，涵盖：设计完成状态、各团队成员的实现状态、测试结果以及任何未解决的问题。
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.
- 2d ago First seen · 72 lines · 49 tokens per session scan A 9bf5b13254bc
team-combat is a skill published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (326 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,011 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
woc-extract-and-test
Implement World of ClaudeCraft features, bug fixes, and focused refactors using module-first design and behavior-driven tests. Use when adding behavior, fixing a defect, extracting logic from a large file, or moving code behind an existing architectural seam.
engine-tdd
Test-first discipline for FlatRedBall2 engine changes. Triggers whenever editing any file under src/ for a behavior change (bug fix or feature). Not for XML docs, renames, style-only edits, or sample code.
unity-tdd
This skill should be used when the user asks to write tests first, do TDD, implement a feature or bugfix using test-driven development, add unit tests before coding, write EditMode or PlayMode tests, or set up Unity Test Runner. Also applies when a user says 'red green refactor', 'write a failing test', or…
godot-tdd
Test-driven development for Godot games. Triggers on: TDD, test, GdUnit4, Gut, unit test, integration test, red-green-refactor.
unity-testing
Unity 6 testing guide. Use when writing unit tests, integration tests, or doing TDD with Unity Test Framework. Covers Edit Mode and Play Mode tests, NUnit attributes ([Test], [UnityTest], [SetUp], [TearDown]), testing MonoBehaviours and coroutines, and CI/CD integration. Based on Unity 6.3 LTS documentation.
unity-testrunner
Unity Test Framework CLI automation and test writing patterns. Masters batchmode execution, NUnit assertions, EditMode/PlayMode testing, and TDD workflows. Use PROACTIVELY for test automation, CI/CD pipelines, or test-driven development in Unity.