Borrowing it
Nothing to install: this file belongs to Ruler4396/dsh-launcher. 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/Ruler4396/dsh-launcher/master/AGENTS.mdgit clone --depth 1 https://github.com/Ruler4396/dsh-launcherWrote 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/ruler4396/dsh-launcher/agents-md)<a href="https://agentmods.dev/instructions/ruler4396/dsh-launcher/agents-md"><img src="https://agentmods.dev/badge/instructions/ruler4396/dsh-launcher/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/ruler4396/dsh-launcher/agents-md"><img src="https://agentmods.dev/badge/instructions/ruler4396/dsh-launcher/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 | $0.02230 | $0.02230 |
| Opus 5.5 | $0.00892 | $0.00892 |
| Sonnet 5.5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
dsh-launcher 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 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — 对本仓库中所有 AI Agent 的强制指示
开始任何任务前，你必须先完整阅读并遵守本文件，以及它指向的架构铁律文档。
🚨 第一优先：架构铁律（不读就动代码 = 违规）
本仓库是 dsh-launcher——一个涉及复杂进程编排、Win32 底层交互与 WebView2 渲染的 Windows 桌面启动器。
在修改任何 .cs 代码、编写测试、调整构建脚本之前，你必须先通读：
docs/00-ARCHITECTURE-GUARDRAILS-MANDATORY.md← 架构与工程维护铁律 v1.0（强制约束，非建议）docs/TESTING-GUARDRAILS.md← 测试体系铁律（SDET 强制约束，Bug 驱动复现）
这份文档是 Hard Constraints（硬约束），不是可选项。违反其中任一条款都会被 Code Review 驳回或 CI 拦截。它规定了：组合根边界、Manager 依赖方向、状态机单一真相源、进程调用的"三必须"、异常透明性、Win32 NC 消息拦截、WebView2 崩溃隔离、契约测试先行等。
测试铁律（尤其重要）：禁止"Mock 幻觉"——涉及进程/文件锁/编码的测试必须补 Category=RealOS 真实 OS 交互测试；修复 P0/P1 环境 Bug 后必须写 Regression_<Bug> 零 Mock 复现测试，否则不予合并（详见 docs/TESTING-GUARDRAILS.md）。
🔥 快速合规清单（动代码前自检）
| 你将要做什么 | 必须先满足 |
|---|---|
改 Program.cs |
只允许组合根 + UI 消息泵；业务逻辑下沉到 Managers//Lifecycle//ShellLogic.cs |
| 调用外部进程（npm/node/taskkill） | node.exe 直启 .js 入口（ADR-021：严禁 cmd.exe / .cmd shim 中间层——引号剥离/GBK 乱码/Kill 不干净三类陷阱；System32 原生 exe 如 taskkill/netstat 可直启）；三必须不变：重定向 stdout/stderr + 异步排空 + 限时等待 + 超时 Kill(entireProcessTree) |
| 读可能被锁的日志文件 | FileShare.ReadWrite |
| 写核心状态文件 | ShellLogic.AtomicWrite（.tmp + File.Move），禁止裸 File.WriteAllText |
| 调用 npm/node | 用 RuntimeManager 解析的绝对路径，禁止盲目依赖 PATH |
加 catch 块 |
禁止空 catch {} / catch { return false; }；区分 Warn 降级 vs Error+E9001 |
| 写任何用户可见错误弹窗 | 必须带 [E####] 错误码 |
修改 ShellLogic 纯函数 |
先补/更新 xUnit 契约测试 |
| 修改生命周期流转 | 在 LauncherAppScenarioTests 补 Headless 测试 |
| 修改窗口布局/DPI/无边框 | 用 --ui-selftest 或 UiTestHookE2ETests 验证 0px 间隙，禁肉眼 |
动 test.ps1 静态断言 |
严禁注释或削弱（God Object 最后防线） |
给用例分一层（[Trait("Category", "RealOS")]） |
逐字拼写、键名必须叫 Category（xUnit 区分大小写，拼错就静默躲过分层）；一条用例只在一层跑；两个 filter 只在 scripts/test.ps1 存一份；1b 闸会红 |
| 断言"仓库里某个真实文件长什么样" | 走 tests/DshShell.Tests/RepoFile.cs（找不到就抛）；禁止 if (!File.Exists) return;——那句 return 就是把断言蒸发掉（2026-09-20 实测 3 条因此从未执行） |
| 加/改 workflow | 必须带 concurrency + cancel-in-progress；声称"我们有 E2E/真机回归"之前，先答出它上一次真实运行的日期（gh run list --workflow <名> --limit 1） |
| 建本地沙盒/测试安装环境 | 只用仓库根 sandbox/ 下子目录（单一沙盒铁律，见 docs/00-ARCHITECTURE-GUARDRAILS-MANDATORY.md 核心约束六）；禁止仓库外另建沙盒；%TEMP% 瞬态隔离用例（neg/drill/CleanData）保持不动 |
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 Changed · -1 lines · -20 tokens per session a794918e7fe8
- 1mo ago Changed · +6 lines · +411 tokens per session e7dfda292e45
- 1mo ago Changed · +171 tokens per session 3f3bb98a1c30
- 2mo ago Changed · +1 lines · +163 tokens per session 456714c215e9
- 2mo ago First seen · 81 lines · 1,505 tokens per session scan A 7364f88d0d5e
dsh-launcher AGENTS.md is an instructions file published in the GitHub repository Ruler4396/dsh-launcher (195 stars, last pushed 1mo ago), licensed MIT. It adds 2,230 tokens to every session, about $0.0089 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.
dsh-launcher AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dsh-launcher AGENTS.mdRuler4396/dsh-launcher | Instructions file | 195 | 1mo ago | MIT | A | 2,230 | 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 |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |