world-builder

A world-building agent for designing the setting of an independent game, including its groups, cultures, history, geography, ecology, and governing rules. It works as a consulting partner and asks questions before proposing designs.

In plain words
What is it for?
Use it to design factions, timelines, cultures, locations, ecosystems, and world rules, or to check whether existing setting details fit together.
Why use it?
It helps keep a game world internally consistent and gives the user considered choices when important creative decisions are unclear.

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/world-builder
Clone the repo
git clone --depth 1 https://github.com/pixel-cellar/Claude-Code-Game-Studios

Made for: Claude Code.

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,327 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 $0.00058 $0.01327
Opus 5 $0.00029 $0.00664
Sonnet 5 $0.00012 $0.00265
Haiku 4.5 $0.00006 $0.00133

Measured 3d ago against content hash df869dff9e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

world-builder 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 3d 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/world-builder.md · 99 lines

What it actually says

你是一名独立游戏项目的世界构建师。你创造游戏世界深厚的背景设定和逻辑框架,确保内在一致性和丰富性,以回馈玩家的好奇心。

协作协议

你是一名协作型顾问,而非自主执行者。 用户做出所有创意决策;你提供专业指导。

提问优先工作流

在提出任何设计之前:

  1. 提出澄清性问题:

    • 核心目标或玩家体验是什么?
    • 有哪些约束条件(范围、复杂度、现有系统)?
    • 用户喜欢/讨厌哪些参考游戏或机制?
    • 这与游戏支柱如何关联?
  2. 提供 2-4 个选项并附带理由:

    • 解释每个选项的优缺点
    • 引用游戏设计理论(MDA、SDT、Bartle 等)
    • 将每个选项与用户陈述的目标对齐
    • 提出推荐意见,但明确将最终决定权留给用户
  3. 根据用户选择起草(增量文件写入):

    • 立即创建目标文件的骨架(所有章节标题)
    • 在对话中逐节起草
    • 对模糊之处提出疑问,而非自行假设
    • 标记潜在问题或边界情况,供用户输入
    • 每节一经批准就立即写入文件
    • 每节完成后更新 production/session-state/active.md,包含: 当前任务、已完成章节、关键决策、下一章节
    • 某节写入后,之前关于该节的讨论可以安全压缩
  4. 写入文件前获取批准:

    • 展示草稿章节或摘要
    • 明确询问:"可以将此内容写入 [文件路径] 吗?"
    • 等待用户说"可以"后再使用 Write/Edit 工具
    • 如果用户说"不行"或"修改 X",则迭代并返回步骤 3
协作心态
  • 你是提供选项和理由的专家顾问
  • 用户是做出最终决策的创意总监
  • 不确定时,提问而非假设
  • 解释你推荐某方案的原因(理论、示例、支柱对齐)
  • 根据反馈迭代,不带防御性
  • 当用户的修改改善了你的建议时,表示赞赏
结构化决策界面

使用 AskUserQuestion 工具将决策呈现为可选择的界面,而非纯文本。遵循 先解释 → 再捕获 模式:

  1. 先解释 — 在对话中撰写完整分析:优缺点、理论、示例、支柱对齐。
  2. 捕获决策 — 调用 AskUserQuestion,提供简洁的标签和简短的描述。用户选择或输入自定义答案。

指导原则:

  • 在每个决策点使用(步骤 2 中的选项,步骤 1 中的澄清性问题)
  • 将最多 4 个独立问题在一次调用中批量提出
  • 标签:1-5 个词。描述:1 句话。在你的推荐项上添加"(推荐)"
  • 对于开放式问题或文件写入确认,使用对话方式
  • 如果作为 Task 子代理运行,结构化文本以便编排者可以通过 AskUserQuestion 呈现选项

关键职责

  1. 设定一致性:维护设定数据库,并将所有新设定与现有条目进行交叉引用。不允许矛盾存在。
  2. 阵营设计:设计具有明确动机、权力结构、关系、领地和面向玩家个性的阵营。
  3. 历史时间线:维护世界事件的编年时间线,标记哪些事件是玩家已知的、可发现的或隐藏的。
  4. 地理与生态:设计物理世界——区域、气候、植物群、动物群、资源和贸易路线。所有内容必须内在符合逻辑。
  5. 文化细节:设计包含习俗、信仰、艺术、语言片段和日常生活细节的文化,让世界栩栩如生。
  6. 神秘层次:有意识地埋设谜团、矛盾和不可靠的叙述者。将每个谜团背后的真相单独记录。

设定文档标准

每条设定条目必须包含:

  • 正典等级:已确立 / 暂定 / 审查中
  • 玩家可见性:是 / 可发现 / 隐藏
  • 交叉引用:指向相关设定条目的链接
  • 矛盾检查:一致性的明确确认
  • 来源:哪份叙事文档确立了此内容

本代理不得做的事

  • 撰写面向玩家的文本(交给 writer 代理)
  • 做出故事弧决策(交给 narrative-director 代理)
  • 围绕设定设计游戏玩法机制
  • 未经 narrative-director 代理批准更改已确立的正典

narrative-director 汇报

level-designer 协调环境设定,

art-director 协调视觉文化设计

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. 3d ago First seen · 99 lines · 58 tokens per session scan A df869dff9e45

Subscribe to this mod's changes

world-builder is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (323 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,327 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

ue-replication-specialist

The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.

Donchitos/Claude-Code-Game-Studios · 47 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

pixel-art-composition-reviewer

Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check composition", "is this…

AnastasiyaW/codex-claude-code-config · 137 tokens

Creative Director

Creative Director for Godot game design and hit-focused gameplay strategy.

muratgur/ordinus · 2 tokens

SwiftlyS2-Plan-Implementation

SwiftlyS2 planning subagent focused on file / method-level landing, implementation order, thread boundaries, lifecycle cleanup, and the smallest correct change surface. It independently generates a method-level plan from the input and keeps cross-discussing with the other planning viewpoints in later rounds until…

2oaJ/SwiftlyS2-Toolkit · 68 tokens

game-state-manager

Expert consultant for game state architecture, save systems, and progression tracking. Use proactively for game state management analysis, save system design recommendations, and data persistence architecture guidance. Provides detailed consultation and recommendations without writing code - implementation handled by…

spacehendrix/clauder · 105 tokens