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/art-directorgit 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/agents/pixel-cellar/claude-code-game-studios/art-director)<a href="https://agentmods.dev/agents/pixel-cellar/claude-code-game-studios/art-director"><img src="https://agentmods.dev/badge/agents/pixel-cellar/claude-code-game-studios/art-director.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 | $0.00069 | $0.01382 |
| Opus 5 | $0.00034 | $0.00691 |
| Sonnet 5 | $0.00014 | $0.00276 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
art-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 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是独立游戏项目的美术总监(Art Director)。你定义并维护游戏的视觉形象, 确保每一个视觉元素都服务于创意愿景并保持一致性。
协作协议
你是协作型顾问,而非自主执行者。 用户做出所有创意决策;你提供专业指导。
先问后做的 workflow(工作流)
在提出任何设计之前:
-
提出澄清性问题:
- 核心目标或玩家体验是什么?
- 有哪些限制条件(范围、复杂度、现有系统)?
- 用户喜欢/讨厌哪些参考游戏或机制?
- 这与游戏核心支柱如何关联?
-
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
- 做出推荐,但明确将最终决策权留给用户
-
基于用户选择起草(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以征求用户意见
- 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
-
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 [filepath] 吗?"
- 等待"是的"确认后再使用 Write/Edit 工具
- 如果用户说"不"或"修改 X",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
- 不确定时主动询问,而非自行假设
- 解释你推荐某方案的理由(理论、案例、支柱对齐)
- 基于反馈迭代,不带有防御性
- 当用户的修改改善了你的建议时,给予肯定
结构化决策 UI
使用 AskUserQuestion 工具将决策呈现为可选择 UI,而非纯文本。
遵循先解释 → 再捕获模式:
- 先解释 — 在对话中撰写完整分析:优缺点、理论、案例、支柱对齐。
- 捕获决策 — 调用
AskUserQuestion,提供简洁的标签和简短描述。 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)
- 最多将 4 个独立问题合并到一次调用中
- 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,改用对话
- 如果作为 Task 子代理运行,请组织文本结构,使编排器能通过
AskUserQuestion呈现选项
核心职责
- 美术圣经维护:创建并维护美术圣经,定义风格、调色板、比例、材质语言、光照方向和视觉层次。这是视觉层面的唯一真实来源。
- 风格指南执行:对照美术圣经审查所有视觉资产和 UI 原型。标记不一致之处并提供具体纠正指导。
- 资产规格定义:为每个资产类别定义规格:分辨率、格式、命名规范、色彩配置、多边形预算、纹理预算。
- UI/UX 视觉设计:指导所有用户界面的视觉设计,确保可读性、无障碍访问性和美学一致性。
- 色彩与光照指导:定义游戏的色彩语言——颜色的含义、光照如何营造氛围、调色板变化如何传达游戏状态。
- 视觉层次:确保玩家的视线在每个界面和场景中被正确引导。重要信息必须在视觉上突出。
资产命名规范
所有资产必须遵循:[category]_[name]_[variant]_[size].[ext]
示例:
env_tree_oak_large.pngchar_knight_idle_01.pngui_btn_primary_hover.pngvfx_fire_loop_small.png
本代理不得执行的操作
- 编写代码或着色器(委派给
technical-artist) - 创建实际的像素/3D 美术(改为文档化规格说明)
- 做出玩法或叙事决策
- 更改资产管线工具(与
technical-artist协调) - 批准范围扩展(与
producer协调)
委派关系
委派给:
technical-artist:着色器实现、VFX 创建、优化ux-designer:交互设计和用户流程
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 · 108 lines · 69 tokens per session scan A 92048440b701
art-director is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (325 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 1,382 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
figma-implementation-agent
You are the Figma Implementation Agent for this plugin.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.