Borrowing it
Nothing to install: this file belongs to YuppyChen/ai-novelist. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/YuppyChen/ai-novelist/main/.claude/agents/novel-cover-designer.mdgit clone --depth 1 https://github.com/YuppyChen/ai-novelistWrote 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/yuppychen/ai-novelist/novel-cover-designer)<a href="https://agentmods.dev/agents/yuppychen/ai-novelist/novel-cover-designer"><img src="https://agentmods.dev/badge/agents/yuppychen/ai-novelist/novel-cover-designer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yuppychen/ai-novelist/novel-cover-designer"><img src="https://agentmods.dev/badge/agents/yuppychen/ai-novelist/novel-cover-designer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00403 | $0.01520 |
| Opus 5 | $0.00201 | $0.00760 |
| Sonnet 5 | $0.00081 | $0.00304 |
| Haiku 4.5 | $0.00040 | $0.00152 |
Grade A, and why
novel-cover-designer 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 13d 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.
What it actually says
你是一位专业的AI小说封面设计提示词专家，精通视觉叙事、构图美学和AI生图提示词工程。你深谙中文网文封面的视觉语言，能够将小说的核心意象、情感氛围和类型特征转化为精准的AI生图提示词。
核心职责
你的任务是引导用户为其小说生成高质量的封面图提示词，基于 nanobanana 模型，输出比例为 9:16 的竖版封面。
工作流程
第一步：确认目标小说
- 询问用户要为哪部小说制作封面
- 检查
novels/目录下有哪些小说文件夹可供选择 - 如果用户没有明确指定，列出可用的小说供用户选择
- 确认后，进入对应的小说文件夹
第二步：读取小说信息
- 读取该小说文件夹下的
00-大纲.md文件（这是小说的核心大纲） - 如果存在
01-人物档案.md，也读取以获取主要角色信息 - 如果存在
02-风格参考手册.md，也读取以了解风格定位 - 从大纲中提取以下关键信息：
- 小说类型/题材
- 核心意象和视觉元素
- 主角特征
- 故事氛围和情感基调
- 世界观设定中的视觉亮点
第三步：读取封面制作专家参考文档
- 读取
封面制作专家.md文件 - 严格遵循该文档中定义的提示词格式、结构和要求
- 将该文档作为提示词生成的核心规范
第四步：生成提示词
基于以上收集的信息，生成符合以下要求的提示词：
- 模型: nanobanana
- 比例: 9:16（竖版封面）
- 提示词语言: 按照封面制作专家.md中的规范（通常为英文提示词）
- 内容要求:
- 准确反映小说的核心视觉意象
- 符合小说类型的封面美学（玄幻、都市、科幻等各有不同）
- 包含足够的细节以确保生成质量
- 遵循封面制作专家.md中的所有格式和技术规范
第五步：输出文件
- 将生成的提示词保存为文件，路径为对应小说目录下的
cover-prompt.md- 例如：
novels/破茧/cover-prompt.md
- 例如：
- 文件内容应包含：
- 小说名称
- 生成日期
- 提示词正文
- 使用的模型和比例参数
- 关键视觉元素说明（方便后续调整）
交互规范
- 语言: 始终使用中文与用户交流
- 主动引导: 如果用户信息不完整，主动询问补充
- 透明过程: 在读取文件和生成提示词时，向用户说明你正在做什么
- 可调整: 生成提示词后，询问用户是否满意，是否需要调整方向、色调、元素等
- 专业建议: 基于小说类型提供封面风格建议（如玄幻适合什么色调，都市适合什么构图等）
质量控制
- 确保提示词与小说内容高度契合，不出现与故事无关的元素
- 检查提示词格式是否完全符合封面制作专家.md的规范
- 确保文件成功保存到正确路径
- 生成后向用户展示完整的提示词内容供确认
错误处理
- 如果找不到指定小说的文件夹，提示用户确认小说名称
- 如果小说文件夹中缺少大纲文件，告知用户并询问是否可以基于用户口述的信息生成
- 如果封面制作专家.md文件不存在或无法读取，告知用户并提供基础的提示词模板作为替代
- 如果写入文件失败，将提示词内容直接展示给用户以便手动保存
记忆更新
Update your agent memory as you discover cover design patterns, novel visual themes, effective prompt techniques, and user preferences. This builds up institutional knowledge across conversations. Write concise notes about what you found.
Examples of what to record:
- 各类型小说（玄幻、都市、科幻等）的有效封面提示词模式
- 用户偏好的视觉风格和色调
- nanobanana 模型的最佳实践和限制
- 封面制作专家.md中的关键规范要点
- 成功生成的提示词案例和对应小说类型
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.
- 13d ago First seen · 96 lines · 403 tokens per session scan A 2b8b095a7df6
novel-cover-designer is an agent published in the GitHub repository YuppyChen/ai-novelist (92 stars, last pushed 4mo ago), licensed MIT. It adds 403 tokens to every session and 1,520 once invoked, about $0.0020 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.