Borrowing it
Nothing to install: this file belongs to qoli/localclash-luci. 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/qoli/localclash-luci/main/AGENTS.mdgit clone --depth 1 https://github.com/qoli/localclash-luciWrote 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/qoli/localclash-luci/agents-md)<a href="https://agentmods.dev/instructions/qoli/localclash-luci/agents-md"><img src="https://agentmods.dev/badge/instructions/qoli/localclash-luci/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/qoli/localclash-luci/agents-md"><img src="https://agentmods.dev/badge/instructions/qoli/localclash-luci/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 | $0.00892 | $0.00892 |
| Opus 5.5 | $0.00357 | $0.00357 |
| Sonnet 5.5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
localclash-luci 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 3d 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
Repository Guidelines
项目关系
本仓库负责 localClash 的 OpenWrt LuCI 包装层：LuCI 视图、rpcd ACL、 OpenWrt 包元数据、helper 脚本、init 集成，以及面向路由器用户的 UI 行为。
/Volumes/Data/Github/localClash 是相邻的核心仓库。runtime 逻辑、产品级
CLI/MCP API、生成的运行时资产、Mihomo 生命周期和配置渲染都应保留在核心仓库。
LuCI 应调用这些产品接口，不要复制 runtime 逻辑。
表达语言
LuCI 面向用户的表达语言维持为简体中文。
以下内容使用简体中文：
- LuCI UI 标签、描述、按钮文本、状态文本和弹窗摘要。
- rpcd helper 消息和用户可见的 JSON summary。
- 新增到本 LuCI 仓库的文档。
除非用户明确要求繁体中文版本，不要在 LuCI 面向用户的文本中引入繁体中文。
开发注意事项
优先沿用当前应用已经使用的直接 rpcd action 模式。这个 LuCI surface 不是传统 表单加应用的工作流；runtime、接管、恢复和维护控制都是直接操作按钮。
交付前，对改动过的 surface 运行聚焦的语法和打包检查，例如：
sh -n openwrt/luci-app-localclash/root/usr/libexec/rpcd/localclashbash -n scripts/test-rpcd-takeover-restore.shscripts/test-rpcd-takeover-restore.shscripts/build-openwrt-ipk.shscripts/build-openwrt-apk.sh
功能测试与发布选测
从相邻 Core 仓库的 docs/istoreos-test-features.md 和
测试 Skill 开始：维护每个功能最后实际测试版本、结果和证据，
按变更影响选择回归，核对后沿用未受影响功能的历史结果。发布不自动触发全表重测。
集成约束
先在 Core 核对版本化 runtime facts 契约及发布兼容性，再修改 LuCI。fw4/nft、
策略路由、DNS hijack、desired state、ownership marker、boot/hotplug 及跨模块事务归 LuCI；
不得把这些执行器移进 Core，或用未协调的 effective=false 轮询覆盖用户明确停止。
同 boot 修复只依本次启动的拥有证据；跨 reboot 自动恢复是单独、明确的持久设置。
手动停止应清除本次启动的修复意图，不得偷偷启用或改写开机恢复策略。
普通 IPK/APK 只安装静态包文件；postinst 不下载 Core、不创建运行时资产、不管理 MCP 生命周期。下载、service ensure/restart 与任务交接由显式 helper 操作负责。 UI 通过窄 rpcd action 调用正式产品接口，不执行任意 shell、不编辑生成 YAML， 不扩成第二套配置模型或完整规则／群组编辑器。网站分流是受限例外。 保存后不回显订阅秘密；各变更入口读回实际状态，不以 task 完成代替网络结果。
DNS ingress 租约、loopback 本地回查 bypass 与 dnsmasq 上游保持各自职责： LAN 查询不能仅因目标是路由器地址就绕过接管；不得删除 Mihomo 回查 dnsmasq 的 loopback bypass。避免持久覆盖用户 fw4 配置，清理仅处理本模块拥有的规则和 marker。
发布操作按 Core 的 发布 Skill 执行；源码、schema 和 workflow 保持实现事实，README 维护用户入口。
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.
- 3d ago First seen · 64 lines · 892 tokens per session scan A bec04fe49271
localclash-luci AGENTS.md is an instructions file published in the GitHub repository qoli/localclash-luci (121 stars, last pushed 3d ago), licensed MIT. It adds 892 tokens to every session, about $0.0036 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 2026-10-26.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.