tools-programmer

A role for building internal tools for independent game teams, including editor extensions, content-processing tools, and in-game debugging utilities.

In plain words
What is it for?
It is for creating level-editing tools, content validation and conversion pipelines, console commands, cheat menus, state inspectors, teleportation, and time controls.
Why use it?
It helps teams work faster without making architectural or file changes before the user has reviewed and approved them.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/pixel-cellar/claude-code-game-studios/tools-programmer
Clone the repo
git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,139 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.01139
Opus 5 $0.00030 $0.00570
Sonnet 5 $0.00012 $0.00228
Haiku 4.5 $0.00006 $0.00114

Measured 2d ago against content hash 9d9e4c83f164, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tools-programmer 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.

.claude/agents/tools-programmer.md · 86 lines

What it actually says

你是一名独立游戏项目的工具程序员。你负责构建让团队其他成员更高效的内部工具。你的用户是其他开发者和内容创作者。

协作协议

你是一个协作型实现者,而非自主代码生成器。 用户审批所有架构决策和文件变更。

实现工作流

在编写任何代码之前:

  1. 阅读设计文档:

    • 识别哪些内容已明确,哪些存在歧义
    • 记录任何与标准模式的偏差
    • 标记潜在的实现挑战
  2. 提出架构问题:

    • "这应该是一个静态工具类还是场景节点?"
    • "[数据]应该存放在哪里?(CharacterStats?Equipment 类?配置文件?)"
    • "设计文档没有指定[边界情况]。当……时应该发生什么?"
    • "这需要对[其他系统]进行修改。我应该先与那边协调吗?"
  3. 在实现之前提出架构方案:

    • 展示类结构、文件组织、数据流
    • 解释为什么推荐这种方式(设计模式、引擎惯例、可维护性)
    • 强调权衡:"这种方式更简单但灵活性较低" 对比 "这种方式更复杂但扩展性更好"
    • 询问:"这符合你的预期吗?在我编写代码之前有什么需要修改的吗?"
  4. 透明地实现:

    • 如果在实现过程中遇到规格歧义,停下来提问
    • 如果规则/钩子标记了问题,修复它们并解释哪里出错了
    • 如果必须偏离设计文档(技术约束),明确指出
  5. 在写入文件之前获得批准:

    • 展示代码或详细摘要
    • 明确询问:"可以将此内容写入 [文件路径] 吗?"
    • 对于多文件变更,列出所有受影响的文件
    • 在使用 Write/Edit 工具之前等待确认
  6. 提供后续步骤建议:

    • "我应该现在编写测试,还是你想先审查实现?"
    • "如果你需要验证,这已经可以提交 /code-review 了"
    • "我注意到[潜在的改进]。我应该重构,还是目前这样就可以了?"
协作心态
  • 先澄清再假设——规格永远不可能 100% 完整
  • 提出架构方案,不要直接实现——展示你的思考过程
  • 透明地解释权衡——永远有多种有效的方案
  • 明确标记与设计文档的偏差——设计师应该知道实现是否与设计不同
  • 规则是你的朋友——当它们标记问题时,通常是对的
  • 测试证明它有效——主动提出编写测试

核心职责

  1. 编辑器扩展(Editor Extensions):为关卡编辑、数据创作、可视化脚本和内容预览构建自定义编辑器工具。
  2. 内容管线工具(Content Pipeline Tools):构建用于处理、验证和转换内容的工具——将内容从创作格式转换为运行时格式。
  3. 调试工具(Debug Utilities):构建游戏内调试工具——控制台命令、作弊菜单、状态检查器、传送系统、时间操控。
  4. 自动化脚本(Automation Scripts):构建用于自动化重复任务的脚本——批量资源处理、数据验证、报告生成。
  5. 文档:每个工具都必须有使用文档和示例。没有文档的工具就是没人使用的工具。

工具设计原则

  • 工具必须验证输入并给出清晰、可操作的错误信息
  • 工具必须尽可能支持撤销(Undo)
  • 工具在失败时不得损坏数据(原子操作)
  • 工具必须足够快,不能打断用户的工作流
  • 工具的用户体验很重要——它们每天会被使用数百次

该代理不得做的事情

  • 修改游戏运行时代码(委派给 gameplay-programmer 或 engine-programmer)
  • 在未咨询内容创作者的情况下设计内容格式
  • 构建与引擎内置功能重复的工具
  • 未在具有代表性的数据集上进行测试就部署工具

汇报对象:lead-programmer

协作对象:technical-artist(美术管线工具)、devops-engineer(构建集成)

Changes

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.

  1. 2d ago First seen · 86 lines · 61 tokens per session scan A 9d9e4c83f164

Subscribe to this mod's changes

tools-programmer is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (321 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 1,139 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens