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/weiweigogo/openfrence/claude-mdgit clone --depth 1 https://github.com/weiweigogo/openFrenceWrote 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/weiweigogo/openfrence/claude-md)<a href="https://agentmods.dev/instructions/weiweigogo/openfrence/claude-md"><img src="https://agentmods.dev/badge/instructions/weiweigogo/openfrence/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 | $0.00596 | $0.00596 |
| Opus 5 | $0.00298 | $0.00298 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
openFrence 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 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.
What it actually says
openFences
Stardock Fences 的开源替代。Windows 桌面图标分组管理工具，使用 C++/Win32 原生构建。
核心架构
- 语言: C++17（MSVC v141 工具链，VS2017），
CMAKE_CXX_STANDARD 20 - 窗口: Win32 原生
WS_CHILD窗口，挂载在 explorer 的SysListView32桌面图标列表下 - 渲染: Direct2D + DirectWrite + WIC，
WS_EX_LAYERED+UpdateLayeredWindow管线 - 序列化: nlohmann/json，配置文件
%APPDATA%\openFences\config.json - 构建: CMake 3.20+，MSVC（VS2017 generator），x64，
/MT静态链接 CRT - 产物: 单 exe（~780KB），无依赖，便携运行
源文件（cpp/src/）
| 文件 | 职责 |
|---|---|
main.cpp |
入口、托盘菜单、桌面图标管理、隐藏/显示调度 |
fence_window.cpp |
Fence 窗口：创建、拖拽、缩放、折叠、重命名、右键菜单 |
render.cpp |
Direct2D 渲染管线：毛玻璃（Acrylic）、边框、文字、布局 |
context_menu.cpp |
Win11 风格 Fluent 自绘菜单 + LL 钩子关闭 |
settings_panel.cpp |
外观设置面板（背景色、标题色、对齐、字体大小等） |
config.cpp |
配置持久化（读写 JSON、自动保存、开机自启注册表） |
icon_extract.cpp |
从文件/快捷方式提取图标像素数据 |
menu_icons.cpp |
菜单项图标的程序化光栅化（矢量字形） |
构建与运行
cmake --build cpp/build --config Release --target openfences
cpp/build/Release/openfences.exe
编码约定
- 无注释解释"做什么"（命名即文档），注释仅解释"为什么"
- 禁止每帧/热路径上的堆分配（笔刷缓存复用
SetColor） - 所有 GDI/D2D/WIC 资源在窗口销毁时 RAII 释放
- UI 统一：颜色、间距、字体等全局常量定义，禁止硬编码
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 · 40 lines · 596 tokens per session scan A ddbcfb3d1c33
openFrence CLAUDE.md is an instructions file published in the GitHub repository weiweigogo/openFrence (69 stars, last pushed 17d ago), licensed MIT. It adds 596 tokens to every session, about $0.0030 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
xiaozhi-esp32 AGENTS.md
AGENTS.md instructions for 78/xiaozhi-esp32, covering agents.md, project, architecture, required rules and boards and configuration.
intelligent-terminal copilot-instructions.md
Copilot instructions for microsoft/intelligent-terminal, covering copilot instructions for windows terminal, build, running, test and code formatting.
SQLiteCpp copilot-instructions.md
Instructions for SRombauts/SQLiteCpp, covering sqlitecpp llm coding guide, non-negotiables (must follow), workflow (common tasks), add a method and add a class.
ai-code-interface.el AGENTS.md
Instructions for tninja/ai-code-interface.el, covering agents.md, common development commands, byte compilation, running tests and run a specific test file.
monkey AGENTS.md
Instructions for monkey/monkey, covering agents, repository map, main runtime flow, build and verification and commit style used in this repository.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).