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/dorakoo/doubao-studio/agents-mdgit clone --depth 1 https://github.com/dorakoo/doubao-studioWrote 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/dorakoo/doubao-studio/agents-md)<a href="https://agentmods.dev/instructions/dorakoo/doubao-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/dorakoo/doubao-studio/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 5.1 | $0.01510 | $0.01510 |
| Opus 5 | $0.00755 | $0.00755 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
doubao-studio 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 5d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
项目概览
豆包工作室 Doubao Studio Desktop - 面向 AI 内容创作者的多账号管理与自动化生产工作台。Electron 桌面应用，左侧多账号管理+任务调度控制台，右侧会话隔离的内嵌豆包浏览器。
技术栈
- 运行时: Electron 33 + Node.js 24
- 前端: React 18 + TypeScript 5 + Ant Design 5 + Tailwind CSS 3
- 状态管理: Zustand 5
- 构建: Vite 6 (渲染进程) + tsc (主进程) + electron-builder (打包)
- 包管理: pnpm
项目结构
├── main/ # 主进程 (Electron Main Process)
│ ├── main.ts # 应用入口：窗口创建、IPC 注册
│ ├── preload.ts # 预加载脚本：contextBridge 暴露 API
│ ├── core/ # TaskService、Repository、事件流等任务域核心
│ ├── cli/ # 只读查询与受控 CSV 导入 CLI
│ ├── mcp/ # MCP stdio 服务端与客户端
│ ├── ipc/
│ │ ├── accounts.ts # 账号管理 IPC (CRUD + Session 隔离)
│ │ └── tasks.ts # 任务调度 IPC (队列管理 + 状态流转)
│ └── utils/ # 持久化、启动、额度与媒体辅助逻辑
├── packages/contracts/ # 主进程/渲染进程共享的纯类型契约
├── schemas/capability/v1/ # 对外 Capability API JSON Schema
├── src/ # 渲染进程 (React)
│ ├── index.tsx # React 入口 + Ant Design ConfigProvider
│ ├── App.tsx # 主布局：三栏式 + 拖拽调整宽度
│ ├── components/
│ │ ├── Toolbar.tsx # 顶部工具栏
│ │ ├── Sidebar.tsx # 左侧面板容器（上下分区）
│ │ ├── AccountList.tsx # 账号列表
│ │ ├── TaskConsole.tsx # 任务控制台
│ │ └── BrowserPanel.tsx # 内嵌浏览器（webview）
│ ├── store/
│ │ ├── useAccountStore.ts # 账号状态管理
│ │ └── useTaskStore.ts # 任务状态管理
│ ├── types/
│ │ ├── index.ts # 全局类型定义
│ │ └── electron.d.ts # Electron API 类型声明
│ └── styles/
│ └── global.css # Tailwind + 自定义组件样式
├── tests/unit/ # Node/Vitest 行为与边界测试
├── docs/ # 架构设计、handoff 与 README 图文资产
├── examples/ # CSV 模板与适配规则示例
├── package.json
├── tsconfig.json # 基础 TS 配置
├── tsconfig.main.json # 主进程 TS 配置 (CommonJS)
├── tsconfig.renderer.json # 渲染进程 TS 配置 (ESNext + JSX)
├── vite.config.ts # Vite 配置
├── tailwind.config.js # Tailwind 配置（品牌色系）
├── .coze # 沙箱构建/运行配置
└── DESIGN.md # 设计规范
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.
- 5d ago First seen · 107 lines · 1,510 tokens per session scan A 03c092f38744
doubao-studio AGENTS.md is an instructions file published in the GitHub repository dorakoo/doubao-studio (50 stars, last pushed 7d ago), licensed MIT. It adds 1,510 tokens to every session, about $0.0076 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
SeedanceMCP CLAUDE.md
Claude Code instructions for AceDataCloud/SeedanceMCP, covering seedancemcp, project structure, sync from docs and development.
velorn AGENTS.md
AGENTS.md instructions for VelornLabs/velorn, a project described as: AI-native video editing built around real creative timelines, generative workflows, and local agent control.
SeedanceMCP copilot-instructions.md
Copilot instructions for AceDataCloud/SeedanceMCP, covering copilot instructions for seedancemcp, sync from docs, project structure and development.
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.