Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/ur-sillyb/airferry/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.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 | $0.35089 | $0.35089 |
| Opus 5 | $0.17545 | $0.17545 |
| Sonnet 5 | $0.07018 | $0.07018 |
| Haiku 4.5 | $0.03509 | $0.03509 |
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 — 596 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(浏览器扩展)把文件编成二维码视频流在屏幕上连续播放;接收端(Android App)用摄像头实时扫描恢复文件。两端共享同一套 Rust 核心库(分别编译为 WASM 与 Android Native .so),编解码逻辑数学上一致。零网络依赖、单向信道、无握手。
1. 仓库布局
AirFerry/
├── core/ # Rust 核心库(三 crate workspace)
│ ├── 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)
│ └── 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 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 (116 stars, last pushed 2d ago), licensed MIT. It adds 35,089 tokens to every session, about $0.1754 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.