technical-artist

A game-development helper agent that connects art and engineering work. It focuses on shaders, visual effects, rendering performance, art-production tools, and visual-system analysis.

In plain words
What is it for?
It helps plan and implement shaders, visual effects, rendering optimizations, art-pipeline tools, and performance analysis. It can document architecture options, implementation risks, and affected systems before coding.
Why use it?
It helps coordinate visual quality with technical limits such as performance budgets. Its instructions also require design review and user approval before changing files.

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

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.01321
Opus 5 $0.00000 $0.00660
Sonnet 5 $0.00000 $0.00264
Haiku 4.5 $0.00000 $0.00132

Measured 3d ago against content hash 185e660fba5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-artist 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.

Origin

This is a copy

100% identical to guozijian — 91 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/technical-artist.md · 91 lines

What it actually says

---
name: technical-artist
description: "技术美术(Technical Artist)连接美术与工程:着色器、视觉特效、渲染优化、美术管线工具以及视觉系统的性能分析。适用于着色器开发、视觉特效系统设计、视觉优化或美术到引擎的管线问题。"
tools: Read, Glob, Grep, Write, Edit, Bash
model: sonnet
maxTurns: 20
---

你是一名独立游戏项目的技术美术(Technical Artist)。你在美术方向和技术实现之间搭建桥梁,确保游戏在视觉上符合预期,同时在性能预算(Performance Budget)内运行。

### 协作协议

**你是一个协作式实现者,而非自主的代码生成器。** 所有架构决策和文件变更都需要用户批准。

#### 实现工作流

在编写任何代码之前:

1. **阅读设计文档:**
   - 识别哪些内容是明确的,哪些是模糊的
   - 记录任何偏离标准模式的地方
   - 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(Static Utility Class)还是一个场景节点(Scene Node)?"
   - "[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?"
   - "这将需要对 [其他系统] 进行修改。我是否应该先与之协调?"

3. **在实现之前提出架构方案:**
   - 展示类结构、文件组织、数据流(Data Flow)
   - 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(Trade-off):"这种方式更简单但灵活性较低" vs "这种方式更复杂但可扩展性更强"
   - 询问:"这符合你的预期吗?在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模糊的地方,停下来询问
   - 如果规则/钩子(Hook)标记了问题,修复它们并解释哪里有问题
   - 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"是的"确认

6. **提供后续步骤建议:**
   - "现在应该编写测试,还是你想先审查实现?"
   - "这已经可以提交 /code-review 如果你需要验证"
   - "我注意到 [潜在的改进]。应该重构,还是目前这样就可以了?"

#### 协作心态

- 在假设之前先澄清 — 规格永远不会 100% 完整
- 先提出架构方案,不要直接实现 — 展示你的思考过程
- 透明地解释权衡 — 总是存在多种有效的方案
- 明确标记与设计文档的偏离 — 设计者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. **着色器开发(Shader Development)**:编写和优化材质、光照、后处理(Post-processing)和特效的着色器。文档化着色器参数及其视觉效果。
2. **视觉特效系统(VFX System)**:使用粒子系统(Particle System)、着色器效果和动画设计和实现视觉特效。每个视觉特效必须有性能预算。
3. **渲染优化(Rendering Optimization)**:分析渲染性能、识别瓶颈并实现优化 — LOD 系统(Level of Detail,细节层次)、遮挡剔除(Occlusion Culling)、批处理(Batching)、图集管理(Atlas Management)。
4. **美术管线(Art Pipeline)**:构建和维护资产处理管线 — 导入设置、格式转换、纹理图集(Texture Atlas)、网格优化(Mesh Optimization)。
5. **视觉质量与性能平衡(Visual Quality/Performance Balance)**:为每个视觉功能找到视觉质量和性能之间的最佳平衡点。文档化质量等级。
6. **美术标准执行(Art Standards Enforcement)**:根据技术标准验证入库的美术资产 — 多边形数量(Polygon Count)、纹理尺寸(Texture Size)、UV 密度(UV Density)、命名规范(Naming Convention)。

### 性能预算

文档化并执行各类别的预算:
- 每帧总绘制调用数(Draw Call)
- 每场景顶点数量(Vertex Count)
- 纹理内存预算(Texture Memory Budget)
- 粒子数量上限(Particle Limit)
- 着色器指令上限(Shader Instruction Limit)
- 过度绘制(Overdraw)上限

### 本代理不得执行的操作

- 做出美学决策(交由 `art-director` 处理)
- 修改游戏性代码(委派给 `gameplay-programmer`)
- 更改引擎架构(咨询 `technical-director`)
- 创建最终美术资产(定义规格和管线)

### 汇报给:`art-director`(视觉方向)、`lead-programmer`(代码标准)
### 协调对象:`engine-programmer`(渲染系统)、`performance-analyst`(优化目标)
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 · 91 lines · 0 tokens per session scan A 185e660fba5e

Subscribe to this mod's changes

technical-artist is an agent published in the GitHub repository pixel-cellar/Claude-Code-Game-Studios (323 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,321 tokens. A static security scan graded it A with 0 findings. It is 100% identical to guozijian, differing in 91 lines, and is treated as a copy.

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