Borrowing it
Nothing to install: this file belongs to dabaicai001/star-dsh-desktop. 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/dabaicai001/star-dsh-desktop/main/AGENTS.mdgit clone --depth 1 https://github.com/dabaicai001/star-dsh-desktopWrote 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/dabaicai001/star-dsh-desktop/agents-md)<a href="https://agentmods.dev/instructions/dabaicai001/star-dsh-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/dabaicai001/star-dsh-desktop/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/dabaicai001/star-dsh-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/dabaicai001/star-dsh-desktop/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 | $0.03349 | $0.03349 |
| Opus 5 | $0.01674 | $0.01674 |
| Sonnet 5 | $0.00670 | $0.00670 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
star-dsh-desktop 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 today.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — StarHub 协作指引
写给 AI Agent 和人类贡献者:读完这份文件就能上手改这个仓库。架构级变更请同步更新 docs/ 与本文件。
项目是什么
StarHub 是跨平台(Windows / macOS / Linux)DevOps 桌面应用,单一窗口整合:数据库客户端(MySQL / PostgreSQL / SQLite / Redis / ClickHouse / SQL Server / Elasticsearch)、SSH 终端、SFTP、Docker 面板、AI 助手。
| 项 | 值 |
|---|---|
| 仓库 | https://github.com/dabaicai001/star-dsh-desktop |
| 主分支 | main |
| 协议 | MIT |
| 当前版本 | v0.116.9(SFTP「跟随终端」只在手敲 pwd 后才跟随,cd 不触发:终端 cwd 三处断点叠加导致 OSC 7 自动上报链路对多数真实环境从未生效——① stripTerminalControl 的转义分支顺序错误,C0 esc-dispatch 备选([@-Z\\-_])把 \x1B] 的 ](0x5D)当作单字符转义先吃掉,OSC 分支成死代码,带 OSC 0 标题 / ANSI 颜色的 PS1(Ubuntu 默认)剥离后 payload 残留,isShellPromptLine 永远识别不出 prompt → 注入永不发生;② prompt 识别与注入解耦后仍要等「下一个 chunk」,连接后直接操作 SFTP 从不敲终端的用户永远注入不了;③ fish 等 shell 对 bash 方言注入命令免疫。现修复正则分支顺序(OSC 分支提前、payload 剥净),prompt 识别在控制序列剥离后进行并在同一 chunk 完成注入,建链静默 exec 增加 echo $0; ps -p $$ -o comm= 登录 shell 探测(bash/zsh 用原 hook、fish 走 --on-event fish_prompt 事件、csh/tcsh 等免疫 shell 不注入),并新增第三条 cwd 信号——从 prompt 行提取路径(\u@\h:\w\$、[root@host ~]# 等默认 PS1,~ 按登录 home 展开)。四层叠加后:默认配置下 cd 即跟随,无需再敲 pwd。) |
架构一句话
三层进程:Rust 主进程(Tauri 2,src-tauri/) 管窗口、SSH/SFTP、密钥环、AI 浏览器 → Go Sidecar(sidecar/) 经 stdio JSON-RPC 管全部数据库/中间件适配 → 前端 是 DeepSeek Harness 主壳 + StarHub React 工作台(vendor/deepseek-harness/,git submodule)。
目录结构
starhub/
├── src-tauri/ # Rust 主进程(Tauri 2)
│ ├── src/
│ │ ├── main.rs # 入口(主窗口关闭联动销毁其余窗口)
│ │ ├── commands/ # 全部 Tauri Command:ssh / sftp / db / docker / ai_memory /
│ │ │ # android(Android 设备设置)/ asset / audit / alert / broker /
│ │ │ # browser / desktop(沙箱桌面 UI)/ dsh_plugins / file / harness /
│ │ │ # local / mcp / screenshot / secret / sidecar
│ │ ├── ssh/ # SSH 会话(russh):auth / session / known_hosts / sftp_transport
│ │ ├── sftp/ # SFTP 会话与传输(russh-sftp)
│ │ ├── android/ # Android 实体机(adb):mod(授权/直播双模/scrcpy 通道/20 工具)
│ │ ├── browser/ # AI 浏览器(无痕独立窗口):mod / script / cdp(Win)/ snapshot_*(mac/Linux)
│ │ ├── desktop/ # 沙箱桌面(Ubuntu 容器沙箱平台):mod(编排/授权/接管)/ recipe(配方)
│ │ ├── harness/ # dsh 桥与插件宿主(harness/plugins)
│ │ ├── db/ # 本地 SQLite 持久化(sqlx)
│ │ ├── keyring/ # 系统 Keyring 封装
│ │ └── sidecar/ # Go Sidecar 启动器
│ ├── capabilities/ # Tauri 权限(按窗口收窄)
│ └── tauri.conf.json
│
├── sidecar/ # Go 1.25 Sidecar — 数据库/中间件代理
│ ├── main.go # stdio JSON-RPC server 入口
│ ├── adapters/ # mysql / postgres / sqlite / redis / clickhouse / mssql /
│ │ # elasticsearch / broker(Kafka/NSQ)/ docker(+compose,+ssh)/ excel / csv / backup
│ ├── pool/ rpc/ # 连接池 / JSON-RPC 协议
│ └── bin/ # 构建输出 starhub-sidecar[.exe]
│
├── vendor/deepseek-harness/ # DSH 主壳与 StarHub React 工作台(唯一 git submodule)
│ ├── apps/
│ │ ├── starhub-window/ # StarHub 资产工作台构建入口(产物 dist-starhub-react/)
│ │ ├── web/ cli/ # DSH 自身应用
│ └── packages/starhub/ # 11 个内置插件:approval-bridge / client-nav / commit-message /
│ # domain-events / host-static / live-context / memory-context /
│ # memory-sink / session-registry / tool-context / tools
│
├── legacy-core/ # 脱离前端的纯 TS 工具与服务(node --test 覆盖)
├── scripts/ # 构建脚本:build-sidecar / build-window / dev-dsh-shell /
│ # bump-version / cargo-env.bat(MSVC)/ refresh-icons / verify-linux-bundles
├── tests/ # node --test 单测(utils、AI 上下文/滚动/记忆、SSH prompt/cwd/后台任务)
├── docs/ # 技术方案 / 设计系统 / 踩坑记录 / 已知坑索引 / 架构图.html
└── .github/ # CI(lint / test / build / release)
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.
- today Changed · +143 tokens per session 1c8269d56929
- yesterday Changed · +67 tokens per session db0b16b34cd8
- 4d ago Changed · +89 tokens per session 417dd4549efc
- 5d ago Changed · +4 lines · +301 tokens per session 533387c32a51
- 9d ago First seen · 130 lines · 2,749 tokens per session scan A ec86e381e4f3
star-dsh-desktop AGENTS.md is an instructions file published in the GitHub repository dabaicai001/star-dsh-desktop (12 stars, last pushed yesterday), licensed MIT. It adds 3,349 tokens to every session, about $0.0167 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
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.
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.
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).
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).
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.
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.