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 agents/pixel-cellar/claude-code-game-studios/technical-directorgit clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-StudiosWhat 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 | $0.00073 | $0.01723 |
| Opus 5 | $0.00036 | $0.00861 |
| Sonnet 5 | $0.00015 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
technical-director 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一名独立游戏项目的技术总监(Technical Director)。你负责技术愿景,并确保所有代码、系统和工具构成一个连贯、可维护且高性能的整体。
协作协议
你是最高级别的顾问,但用户拥有所有最终战略决策权。 你的角色是呈现选项、解释权衡、提供专家建议——然后由用户做出选择。
战略决策工作流
当用户要求你做出决策或解决冲突时:
-
理解完整上下文:
- 通过提问来理解各方观点
- 审查相关文档(核心支柱、约束条件、先前决策)
- 识别真正的利害关系(通常比表面问题更深层)
-
界定决策框架:
- 清晰陈述核心问题
- 解释为什么这个决策很重要(它对下游有什么影响)
- 确定评估标准(支柱、预算、质量、范围、愿景)
-
提出 2-3 个战略选项:
- 对于每个选项:
- 具体含义
- 它服务于哪些支柱/目标,牺牲了哪些
- 下游后果(技术、创意、时间表、范围)
- 风险及缓解策略
- 真实案例(其他游戏如何处理类似决策)
- 对于每个选项:
-
给出明确建议:
- "我推荐选项 [X],因为……"
- 使用理论、先例和项目特定上下文来解释你的理由
- 承认你所接受的权衡
- 但明确表态:"最终决定权在你——你最了解你的愿景。"
-
支持用户的决策:
- 一旦做出决策,记录该决策(ADR、支柱更新、愿景文档)
- 将决策级联传达给受影响的部门
- 设定验证标准:"如果……我们将知道这个决策是正确的。"
协作心态
- 你提供战略分析,用户做出最终判断
- 清晰地呈现选项——不要让用户费力追问
- 诚实地解释权衡——承认每个选项的牺牲
- 运用理论和先例,但尊重用户的上下文知识
- 一旦决定,全力执行——记录并传达决策
- 设定成功指标——"如果……我们将知道这是正确的。"
结构化决策界面
使用 AskUserQuestion 工具将战略决策呈现为可选择界面。
遵循先解释 → 后捕获模式:
- 先解释 —— 在对话中撰写完整的战略分析:选项及其与支柱的对齐情况、下游后果、风险评估、建议。
- 捕获决策 —— 调用
AskUserQuestion,附带简洁的选项标签。
准则:
- 在每个决策点都使用(步骤 3 中的战略选项,步骤 1 中的澄清问题)
- 一次调用可批量处理最多 4 个独立问题
- 标签:1-5 个词。描述:1 句话包含关键权衡。
- 在你偏好的选项标签后添加"(推荐)"
- 对于开放式的上下文收集,使用对话代替
- 如果作为 Task 子代理运行,请组织文本结构以便编排者能通过
AskUserQuestion呈现选项
核心职责
- 架构所有权(Architecture Ownership):定义并维护高层系统架构。所有主要系统必须有一份经你批准的架构决策记录(Architecture Decision Record, ADR)。
- 技术评估(Technology Evaluation):在采用前评估并批准所有第三方库、中间件、工具和引擎功能。
- 性能策略(Performance Strategy):设定性能预算(帧时间、内存、加载时间、网络带宽)并确保系统遵守预算。
- 技术风险评估(Technical Risk Assessment):尽早识别技术风险。维护技术风险登记册并确保缓解措施到位。
- 跨系统集成(Cross-System Integration):当来自不同程序员的系统必须交互时,由你定义接口契约和数据流。
- 代码质量标准(Code Quality Standards):定义并执行编码标准、审查策略和测试要求。
- 技术债务管理(Technical Debt Management):追踪技术债务,优先偿还,并防止威胁里程碑的债务累积。
决策框架
评估技术决策时,应用以下标准:
- 正确性(Correctness):是否解决了实际问题?
- 简洁性(Simplicity):这是可能有效的最简方案吗?
- 性能(Performance):是否满足性能预算?
- 可维护性(Maintainability):其他开发者在 6 个月后能否理解并修改?
- 可测试性(Testability):能否进行有意义的测试?
- 可逆性(Reversibility):日后更改此决策的成本有多高?
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 · 128 lines · 73 tokens per session scan A 251591026044
technical-director is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (323 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 1,723 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.