Borrowing it
Nothing to install: this file belongs to guoxiucai/ohos-scrcpy-app. 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/guoxiucai/ohos-scrcpy-app/main/CLAUDE.mdgit clone --depth 1 https://github.com/guoxiucai/ohos-scrcpy-appWrote 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/guoxiucai/ohos-scrcpy-app/claude-md)<a href="https://agentmods.dev/instructions/guoxiucai/ohos-scrcpy-app/claude-md"><img src="https://agentmods.dev/badge/instructions/guoxiucai/ohos-scrcpy-app/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/guoxiucai/ohos-scrcpy-app/claude-md"><img src="https://agentmods.dev/badge/instructions/guoxiucai/ohos-scrcpy-app/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 | $0.02446 | $0.02446 |
| Opus 5.5 | $0.00978 | $0.00978 |
| Sonnet 5.5 | $0.00489 | $0.00489 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
ohos-scrcpy-app 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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
OpenHarmony 设备投屏 + HDC 调试工具。Flutter 桌面客户端通过 hdc fport 端口转发与设备上常驻的 OpenHarmony 系统服务通信,实时镜像屏幕并提供触控注入、HAP 安装、HAP卸载、亮度/音量、模拟终端、功能键模拟等控制功能。
沟通规则
- 永远使用简体中文沟通,包括所有回复、注释、提交信息等。
仓库结构
ohos-scrcpy-app/
├── scrcpy_server/ # OpenHarmony 系统应用(ServiceExtension 主体)
│ ├── AppScope/app.json5 # bundleName=com.ohos.scrcpy.server,配置 keepAlive
│ └── entry/src/main/
│ ├── module.json5 # mainElement=ScrcpyService(不是 EntryAbility)
│ ├── ets/
│ │ ├── scrcpyservice/ # 业务全部在此:ScrcpyService、TcpServer、ScreenPipeline、InputInjector、Protocol
│ │ ├── entryability/ # 仅做调试 UI 入口,不写业务
│ │ └── pages/ # 调试页:服务状态、监听端口
│ └── resources/base/element/string.json
├── scrcpy_client_flutter/ # Flutter 桌面客户端(macOS/Windows,Linux 后续)
│ ├── lib/
│ │ ├── hdc/ # 调用系统 hdc CLI(list/fport/install/shell)
│ │ ├── net/ # 协议编解码 + TCP 客户端
│ │ ├── decoder/ # MethodChannel 'scrcpy/decoder' 抽象
│ │ ├── state/app_state.dart
│ │ └── ui/ # top_bar / mirror_view / sidebar / split_view
│ ├── macos/Runner/VideoDecoderPlugin.swift # VideoToolbox + FlutterTexture
│ ├── windows/runner/video_decoder_plugin.* # MFT stub,待补
│ └── scripts/ # package_mac.sh (dmg) / package_win.ps1 (Inno Setup)
└── docs/design.md # 项目设计文档
关键技术决策(已与用户对齐,勿擅自改动)
- HDC 调用方式:客户端
Process.run调系统hdcCLI,优先内置 hdc 二进制文件,其次本机 hdc PATH。 - 视频解码:平台原生硬解(macOS VideoToolbox / Windows MediaFoundation),通过 MethodChannel + Flutter Texture 上屏。不用 media_kit / fvp / ffi+ffmpeg。
- 传输通道:仅
hdc fport tcp:<pcPort> tcp:53535,USB/网络 hdc 共用同一通道,不做设备 LAN 直连。 - 服务端保活与自启:完全交给
app.json5中已配置的keepAlive,不写 BootReceiver/StaticSubscriber,不申请MANAGE_APP_KEEP_ALIVE/RECEIVER_STARTUP_COMPLETED。 - mainElement:
module.json5的mainElement必须指向ScrcpyService(ServiceExtensionAbility),UIAbility 仅作调试 UI 入口,不放业务逻辑。 - API 区间:
compatibleSdkVersion: 15,compileSdkVersion: 23。
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.
- 1mo ago First seen · 133 lines · 2,446 tokens per session scan A e92d66231b7f
ohos-scrcpy-app CLAUDE.md is an instructions file published in the GitHub repository guoxiucai/ohos-scrcpy-app (20 stars, last pushed 22d ago), licensed MIT. It adds 2,446 tokens to every session, about $0.0098 per session on Opus 5.5. 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 2026-09-15.
ohos-scrcpy-app CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ohos-scrcpy-app CLAUDE.mdguoxiucai/ohos-scrcpy-app | Instructions file | 20 | 22d ago | MIT | A | 2,446 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |