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/agent-tower/core/agents-mdgit clone --depth 1 https://github.com/agent-tower/coreWhat 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 | $0.01743 | $0.01743 |
| Opus 5 | $0.00872 | $0.00872 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
core 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tower
AI Agent 任务管理看板应用,支持多种 AI Agent(Codex、Gemini CLI、Cursor Agent、Codex)的任务编排、终端管理和实时协作。
技术栈
| 层级 | 技术 |
|---|---|
| 前端 | React 19 + Vite 7 + TypeScript 5 |
| 样式 | TailwindCSS v4 + shadcn/ui (Radix UI) |
| 状态管理 | TanStack Query v5 (服务端状态) + Zustand v5 (客户端状态) |
| 路由 | react-router-dom v7 (lazy loading) |
| 终端 | xterm.js + Monaco Editor |
| 拖拽 | @dnd-kit |
| 后端 | Fastify 4 + Socket.IO 4 |
| 数据库 | Prisma 5 + SQLite |
| 进程管理 | node-pty |
| 包管理 | pnpm monorepo |
项目结构
packages/
├── shared/ # 共享类型包 (@agent-tower/shared)
├── server/ # 后端服务 (@agent-tower/server)
└── web/ # 前端应用
design/ # 设计文档
docs/ # 项目文档 (ARCHITECTURE.md, PROJECT_SPEC.md, MCP.md 等)
scripts/ # 构建发布脚本 (build-publish.mjs)
CLI 入口
agent-tower— 主服务 (默认端口 12580)agent-tower-mcp— MCP 服务器 (stdio 模式,暴露 projects/tasks/workspaces/sessions/providers tools)
架构设计
Socket.IO
单一命名空间 /events,通过 room-based 订阅区分 topic:
| Room 模式 | 用途 |
|---|---|
session:{id} / session:all |
Agent 会话 PTY 流 |
terminal:{id} / terminal:all |
独立终端 PTY 流 |
task:{id} / task:all |
任务状态变更 |
project:{id} / project:all |
项目级任务更新广播 |
agent:{id} / agent:all |
Agent 状态通知 |
核心机制
- AgentPipeline: PTY + Parser + MsgStore 生命周期管理
- EventBus: 类型安全的进程内事件总线
- 服务容器: 单例管理 (SessionManager, TerminalManager, CommitMessageService, NotificationService)
- 输出解析: Codex / Cursor Agent / Codex 输出解析器,JSON Patch 驱动的 MsgStore
- Git Worktree: 创建/删除/合并/rebase/冲突检测
- 任务状态自动推进: Session 全部完成 → Task 进入 IN_REVIEW;Session 重启 → 回退 IN_PROGRESS
前端状态管理
- TanStack Query: 服务端数据缓存、请求去重、后台刷新
- Zustand: 客户端 UI 状态、Agent 状态
关键目录
packages/server/src/
├── core/ # 服务容器 (DI) + EventBus
├── pipeline/ # AgentPipeline (PTY + Parser + MsgStore)
├── output/ # 输出解析 (Codex-parser, cursor-agent-parser, codex-parser, msg-store)
├── executors/ # Agent 执行器 (Codex, Gemini CLI, Cursor Agent, Codex)
├── mcp/ # MCP 服务器 (tools: projects, tasks, workspaces, sessions, providers)
├── git/ # Git CLI 封装 + WorktreeManager
├── services/ # 业务服务 (session, workspace, project, task, terminal, tunnel, notifications, commit-message, copy-files)
├── routes/ # REST API (16 个路由文件: projects, tasks, sessions, workspaces, terminals, git, files, filesystem, attachments, notifications, profiles, providers, tunnel, system, demo)
├── socket/ # Socket.IO 网关 (/events 命名空间, room 订阅)
│ └── middleware/ # 认证、错误处理
└── middleware/ # HTTP 中间件 (隧道认证)
packages/web/src/
├── layouts/ # RootLayout, SettingsLayout
├── pages/ # HomePage, ProjectKanbanPage, ProjectSettingsPage, ProfileSettingsPage, ProviderSettingsPage, NotificationSettingsPage, DemoPage, AgentDemoPage
├── components/
│ ├── ui/ # shadcn/ui 组件
│ ├── task/ # 任务看板组件 (TaskList, TaskGroup, TaskDetail, StartAgentDialog, ProviderSelector)
│ ├── workspace/ # 终端、编辑器、文件树、Git 变更视图、冲突解决
│ ├── agent/ # 日志流、Todo 面板、Token 用量
│ └── mobile/ # 移动端适配组件
├── hooks/ # TanStack Query hooks (projects, tasks, sessions, workspaces, git, files, attachments, notifications, profiles, providers, tunnel, todos, mobile, token-usage 等)
├── stores/ # Zustand stores (agent-store, ui-store)
├── lib/
│ ├── api-client.ts # HTTP API 客户端
│ └── socket/ # Socket.IO 客户端 + hooks (useTerminal, useStandaloneTerminal, useNormalizedLogs, useTaskRealtimeSync, useWorkspaceSetupProgress)
└── routes/ # react-router-dom 路由配置
packages/shared/src/
├── types.ts # 核心业务类型 (Project, Task, Workspace, Session, TodoItem 等)
├── socket/events.ts # Socket.IO 事件常量与 payload 类型
├── log-adapter.ts # NormalizedEntry → LogEntry 前端适配
└── dev-port.ts # 确定性端口计算
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.
- 2d ago First seen · 140 lines · 1,743 tokens per session scan A e46530fffbd4
core AGENTS.md is an instructions file published in the GitHub repository agent-tower/core (338 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,743 tokens to every session, about $0.0087 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.