Borrowing it
Nothing to install: this file belongs to UR-SillyB/AirFerry. 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/UR-SillyB/AirFerry/main/AGENTS.mdgit clone --depth 1 https://github.com/UR-SillyB/AirFerryWrote 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/ur-sillyb/airferry/agents-md)<a href="https://agentmods.dev/instructions/ur-sillyb/airferry/agents-md"><img src="https://agentmods.dev/badge/instructions/ur-sillyb/airferry/agents-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/ur-sillyb/airferry/agents-md"><img src="https://agentmods.dev/badge/instructions/ur-sillyb/airferry/agents-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 | $0.38035 | $0.38035 |
| Opus 5.5 | $0.15214 | $0.15214 |
| Sonnet 5.5 | $0.07607 | $0.07607 |
| Haiku 4.5 | $0.03803 | $0.03803 |
Grade A, and why
AirFerry AGENTS.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 4d 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 — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI 代理操作手册
本文是给 AI 代理(以及人类开发者)的导航 + 操作索引:怎么构建、怎么定位代码、怎么排错、哪些坑别踩。 本文不重复
docs/*.md的细节,每条都指向权威来源。跨端不变量的位级规格见docs/SPEC.md。 遇到文档与代码冲突时,一律以代码为准(见下方「文档与代码偏差清单」)。 当本文与docs/SPEC.md互相矛盾时(如默认值、常量、行号),先去读对应权威源代码裁决——两份文档都可能滞后,切勿仅凭其中一份下结论。 每次改动代码后,必须同步更新相关文档:改动若涉及常量、默认值、行号、签名、帧格式、文件路径、构建步骤等任一被文档引用的事实,同一提交内回写 AGENTS.md / docs/*.md 的对应位置,勿留滞后(本次审计即是文档滞后于代码的教训)。
项目一句话
AirFerry:完全离线的光学文件传输。发送端把文件编成二维码视频流在屏幕上连续播放,也可由 Python 包输出 MP4;接收端用摄像头或屏幕捕获扫描恢复文件。各端共享同一套 Rust 核心库(WASM、Android Native .so、Windows DLL、Python/PyO3 扩展),编解码逻辑数学上一致。零运行期网络依赖、单向信道、无握手。
1. 仓库布局
AirFerry/
├── core/ # Rust 协议核心(三个核心 crate;workspace 另含 apps/python)
│ ├── raptorq-core/ # RFC 6330 RaptorQ 编解码封装(纯逻辑)
│ ├── qr-protocol/ # 帧格式 / 分块 / 压缩 / CRC / QR 矩阵 / 会话 ID
│ ├── transfer-engine/ # 编排 / 状态机 / 进度 / 断点 / 大文件分段组装 + WASM&JNI&C-ABI 绑定
│ └── zxing-decoder/ # Windows ZXing-C++ 解码核心(非 Cargo crate)
├── apps/
│ ├── sender/ # 浏览器扩展(Plasmo + React + TS + WASM)
│ │ ├── src/ # TS 源码(页面 / WASM 桥 / 压缩 worker / background 图标点击直跳)
│ │ ├── wasm-pkg/ # 当前扩展目标的临时 WASM 快照(generated, git-ignored)
│ │ ├── assets/ # 扩展图标
│ │ └── scripts/ # 构建 / manifest 修正 / lzma-wasm 提取
│ ├── web/ # 网页端(Vite + React + TS)— 直接复用 sender/src 源码,无代码重复
│ │ ├── src/main.tsx # 薄入口:mount sender 的 App(options.tsx)
│ │ ├── scripts/ # prepare-wasm(锁定并复制 sender simd 包 + 拷 zstd)/ lzma 提取
│ │ └── public/ # wasm-zstd.wasm(worker 运行时 fetch,构建时拷入)
│ ├── scanner/ # Android App(Kotlin + CameraX + ZXing-C++)
│ │ └── app/src/main/
│ │ ├── java/com/airferry/app/ # Kotlin
│ │ ├── cpp/ # ZXing-C++ JNI 桥(CMake)
│ │ └── jniLibs/arm64-v8a/ # Rust .so(cargo-ndk 产物, git-ignored)
│ ├── python/ # Python 文件转 MP4(PyO3 + Pillow + 本地 FFmpeg;独立包版本)
│ └── windows/ # Windows App(C# WPF + OpenCvSharp + ZXing-C++)
│ ├── native/ # Windows ZXing C ABI 包装器 + CMake
│ ├── AirFerry.Windows/ # 主项目(Views/ViewModels/Models/Scan/Bundle/Native/Services/Themes;WPF-UI Fluent 主题)
│ │ └── runtime/ # transfer_engine.dll + airferry_zxing.dll(git-ignored)
│ └── AirFerry.Windows.Tests/ # 协议层单元测试(net8.0,跨平台可跑)
├── docs/ # 协议 / 架构 / API / 构建说明(中文)
├── scripts/build-all.sh # 一键构建脚本(含 windows 子命令)
├── scripts/build-windows.ps1 # Windows 端原生 PowerShell 构建脚本(首选)
├── Cargo.toml # Rust workspace 根配置
└── dist/ # 发布产物 + 签名密钥(git-ignored)
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.
- 4d ago Changed · +1 lines · +252 tokens per session 9f78d8429e39
- 6d ago Changed · +35 lines · +2,694 tokens per session 5000ce063b72
- 2mo ago First seen · 596 lines · 35,089 tokens per session scan A c0050226f4f1
AirFerry AGENTS.md is an instructions file published in the GitHub repository UR-SillyB/AirFerry (160 stars, last pushed 4d ago), licensed MIT. It adds 38,035 tokens to every session, about $0.1521 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 2026-08-30.
AirFerry AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AirFerry AGENTS.mdUR-SillyB/AirFerry | Instructions file | 160 | 4d ago | MIT | A | 38,035 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |