Borrowing it
Nothing to install: this file belongs to RoshanGH/mixcut-windows. 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/RoshanGH/mixcut-windows/main/CLAUDE.mdgit clone --depth 1 https://github.com/RoshanGH/mixcut-windowsWrote 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/roshangh/mixcut-windows/claude-md)<a href="https://agentmods.dev/instructions/roshangh/mixcut-windows/claude-md"><img src="https://agentmods.dev/badge/instructions/roshangh/mixcut-windows/claude-md.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 5.1 | $0.16671 | $0.16671 |
| Opus 5 | $0.08335 | $0.08335 |
| Sonnet 5 | $0.03334 | $0.03334 |
| Haiku 4.5 | $0.01667 | $0.01667 |
Grade A, and why
mixcut-windows CLAUDE.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
7. 发 Gitee release：**必须用 PowerShell `Invoke-RestMethod` + UTF8 字节 body**（curl 发中文必乱码）： How it starts
The opening of the file, as written. The whole thing — 672 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
MixCut Windows 版 —— macOS 原生应用 MixCut 的 Windows 移植版， 功能完整对齐。面向广告投放团队的 AI 视频混剪工具：导入广告素材，AI 按语义切分镜头并标注类型， 再智能排列组合生成多条差异化混剪广告。
技术栈：C# + WPF + .NET 8（net8.0-windows），目标系统 Windows 10 及以上（x64）。
🥇 最高原则：商业化 ToC 软件标准（一切环节的总闸 ⚠️⚠️⚠️）
MixCut Windows 不是工程 demo、不是内部工具、不是「能跑就行」的 MVP。它是一款最终要卖给真实付费用户的 ToC 桌面软件，每一个环节都必须按商业化产品的标准来要求。
「无论是哪一个功能，无论写哪一个文档，最终目标是一定要以一个商业化 ToC 软件的要求来要求每一个环节。」—— 项目用户原话（2026-05-29）
适用范围（每一个环节都要套用这把尺）
| 环节 | 商业化 ToC 标准的具体含义 |
|---|---|
| 新功能 | 必须达到本文件 §「商用 C 端软件丝滑标准」全部 10 条；否则不算完成 |
| Bug 修复 | 修一个不能改坏三个；必须自验证再让用户测；故障描述要翻译成人话 |
| UI / 交互 | 像剪映 / Final Cut Pro 一样丝滑，没有静默成功 / 静默失败 / 卡顿 / 神秘消失的窗口 |
| 错误提示 | 不许把 stack trace / JsonException / ExitCode=-XXX 直接丢用户看；必须翻译为人能看懂的描述 + 重试入口 |
| 进度反馈 | 任何 >1s 的操作必须有可视进度；多阶段任务显示「N/M 当前阶段」；细到单个视频/单个文件 |
| 依赖下载 | 国内国外都能用 —— 没国内可访问源就不做依赖下载化（用打包代替） |
| 安装包 | 装上即跑，不挑机器；不能依赖目标机器装过 VS / VC++ Redist / .NET SDK |
| 文档（README / Release notes / Issues） | 用户读得懂；不堆英文报错；Gitee / GitHub 各自当独立发布渠道，不互相引导 |
| 发版 notes | 用户视角讲「新增了什么 / 修了什么 / 怎么下载」；不是 commit log 复制粘贴 |
| 代码注释 / 错误码 | 给未来维护者读 —— 解释为什么这么做，而不是这是什么 |
| 测试与回归 | 改完自验证再让用户测（详见 §「自我验证铁律」）；发版前在干净环境跑完整 e2e |
| issue / PR 描述 | 让 Windows 端 / Mac 端 / 国内代理跑步的工程师都能照着复现 + 实施 |
判定原则（每次完成任务前先自问）
- 这个完成度，敢卖钱吗？ 不敢 → 没完成。
- 真实用户首次打开就能用吗？ 需要他改注册表 / 装 VC Redist / 加白名单 → 没完成。
- 国内国外用户都能正常下载与更新吗？ 一边断了 → 没完成。
- 如果是我自己付了 199 元下载的，我会满意这一段体验吗？ 不会 → 没完成。
- 如果出错了，用户看屏幕能不能知道发生了什么 + 下一步怎么办？ 不能 → 没完成。
红线（任何一条踩中即视为不达标）
- ❌ 发版前没在干净 Win 10/11 环境跑完整 e2e（导入 → ASR → 切分 → 生成方案 → 导出 → 播放）
- ❌ 任何用户面板上能看到的英文 stack trace / 原生报错码
- ❌ 「能跑通」就汇报完成（必须达到 §「商用 C 端软件丝滑标准」基线）
- ❌ 国内 Gitee 渠道引导用户去 GitHub 下载
- ❌ Release notes / issue 描述写得像 commit log，不是给最终用户看的
- ❌ 任何「让用户当第一测试者」的偷懒做法
本节是整个 CLAUDE.md 的总闸 —— 当下游章节的规则与本节冲突时，本节优先。当下游规则需要解释「为什么这么严」，回到本节查就行。
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.
- 8d ago First seen · 672 lines · 16,671 tokens per session scan A a862835e7aa1
mixcut-windows CLAUDE.md is an instructions file published in the GitHub repository RoshanGH/mixcut-windows (56 stars, last pushed 12d ago), licensed MIT. It adds 16,671 tokens to every session, about $0.0834 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.