Borrowing it
Nothing to install: this file belongs to yxhpy/comfy-prompt-studio. 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/yxhpy/comfy-prompt-studio/main/CLAUDE.mdgit clone --depth 1 https://github.com/yxhpy/comfy-prompt-studioWrote 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/instructions/yxhpy/comfy-prompt-studio/claude-md)<a href="https://agentmods.dev/instructions/yxhpy/comfy-prompt-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/yxhpy/comfy-prompt-studio/claude-md/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/instructions/yxhpy/comfy-prompt-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/yxhpy/comfy-prompt-studio/claude-md.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 | $0.03592 | $0.03592 |
| Opus 5 | $0.01796 | $0.01796 |
| Sonnet 5 | $0.00718 | $0.00718 |
| Haiku 4.5 | $0.00359 | $0.00359 |
Grade A, and why
comfy-prompt-studio CLAUDE.md 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 9d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
- 本文件为 CLAUDE 记忆文件,只记录最新的项目状态,保持文件内容的准确性,避免历史记录的干扰
- 使用中文
- 项目必须工程化,方便维护,永远保持文件位置正确
- 永远保证 CLAUDE.md, README.md, AGENTS.md 的内容是准确的,文档和代码一致
- 使用设计模式,保持代码结构清晰,方便维护
- 修复 bug 请先 debug 确认问题所在,再进行修复
- 新增功能先验证功能是否正常,再进行新增
- windows 下必须使用 utf-8 编码,避免中文乱码问题
if sys.platform == 'win32':
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
- 根目录 CLAUDE.md, README.md, AGENTS.md 禁止删除
AI 图像生成 Web 应用:Ollama 提示词增强 + ComfyUI 工作流 + Flask WebSocket 实时更新
架构设计
数据流: 用户输入 → Ollama(提示词增强)→ ComfyUI(图像生成)→ WebSocket → 前端展示
核心模块:
src/cli/run.py- 应用启动入口src/cli/serve.py- Flask 服务器src/app/__init__.py- Flask 应用工厂src/core/prompt/- 提示词生成服务(Ollama/Gemini)src/core/comfyui/- ComfyUI API 集成,自动选择工作流src/core/history/- SQLite 历史记录管理服务
工作流系统:
config/workflows/flowv_normal.json- 普通文生图工作流config/workflows/flow_face.json- 人脸替换工作流- 自动选择逻辑:有
image_path参数时使用人脸工作流
快速启动
前置要求: ComfyUI (127.0.0.1:8188) + Ollama (localhost:11434)
环境配置:
# 1. 复制环境变量模板
cp .env.example .env
# 2. 编辑 .env 文件,填入你的 API 密钥等敏感信息
# 注意:.env 文件包含敏感信息,已在 .gitignore 中忽略
# 3. 安装依赖
pip install -r requirements.txt
启动应用:
python -m src.cli.run
目录结构(工程化)
comfyui/
├── .github/ # GitHub 配置
│ ├── ISSUE_TEMPLATE/ # Issue 模板
│ │ ├── bug_report.md # Bug 报告模板
│ │ └── feature_request.md # 功能请求模板
│ ├── PULL_REQUEST_TEMPLATE.md # PR 模板
│ └── workflows/ # GitHub Actions(待添加)
├── src/ # 源代码目录
│ ├── app/ # Flask 应用模块
│ │ ├── __init__.py # 应用工厂
│ │ ├── config.py # 应用配置
│ │ ├── extensions.py # Flask 扩展
│ │ ├── routes/ # 路由蓝图
│ │ │ ├── api.py # API 路由
│ │ │ └── web.py # Web 路由
│ │ ├── services/ # 业务服务
│ │ │ └── generation.py # 图像生成服务
│ │ └── events/ # WebSocket 事件
│ │ └── generation.py # 生成事件处理
│ ├── cli/ # 命令行工具
│ │ ├── run.py # 应用启动入口
│ │ ├── serve.py # Flask 服务器
│ │ ├── check_import.py # 导入验证工具
│ │ └── migrate_to_sqlite.py # 数据迁移工具
│ ├── core/ # 核心业务逻辑
│ │ ├── comfyui/ # ComfyUI 集成
│ │ │ └── client.py # ComfyUI 客户端
│ │ ├── history/ # 历史记录管理
│ │ │ └── manager.py # 历史记录管理器
│ │ └── prompt/ # 提示词生成
│ │ └── generator.py # 提示词生成器
│ ├── legacy/ # 向后兼容代码
│ ├── models/ # 数据模型
│ ├── routes/ # 路由模块(待迁移)
│ ├── services/ # 业务服务(待迁移)
│ │ └── prompt_service.py # 提示词服务(单例)
│ ├── utils/ # 工具函数
│ └── workers/ # 后台任务
├── config/ # 配置文件
│ ├── workflows/ # ComfyUI 工作流
│ │ ├── flowv_normal.json # 普通文生图
│ │ └── flow_face.json # 人脸替换
│ └── settings.py # 全局配置类
├── templates/ # Jinja2 模板
│ ├── layouts/ # 布局模板
│ │ └── base.html # 基础布局
│ ├── partials/ # 组件模板
│ │ ├── gallery.html # 图片画廊
│ │ ├── history_panel.html # 历史面板
│ │ └── ... # 其他组件
│ └── index.html # 主页
├── static/ # 静态资源
│ ├── css/ # 样式文件
│ │ └── index.css # 主样式
│ ├── js/ # JavaScript 文件
│ │ └── index.js # 主逻辑
│ └── generated/ # 生成图片(旧,向后兼容)
├── data/ # 数据目录
│ ├── generated/ # 生成的图片(不提交)
│ ├── upload/ # 上传的图片(不提交)
│ └── history.db # SQLite 历史记录(不提交)
├── tests/ # 测试文件
├── .env # 环境变量(不提交,敏感信息)
├── .env.example # 环境变量模板
├── .gitignore # Git 忽略配置
├── requirements.txt # Python 依赖
├── LICENSE # MIT 许可证
├── CHANGELOG.md # 版本更新日志
├── CONTRIBUTING.md # 贡献指南
├── CLAUDE.md # 项目技术文档(本文件)
├── README.md # 快速开始指南(用户文档)
└── AGENTS.md # AI 代理配置说明
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.
- 9d ago First seen · 317 lines · 3,592 tokens per session scan A 72ca3c344e28
comfy-prompt-studio CLAUDE.md is an instructions file published in the GitHub repository yxhpy/comfy-prompt-studio (85 stars, last pushed 5mo ago), licensed MIT. It adds 3,592 tokens to every session, about $0.0180 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.