Borrowing it
Nothing to install: this file belongs to agent-tower/core. 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/agent-tower/core/main/.agents/skills/agent-tower-dev/SKILL.mdgit clone --depth 1 https://github.com/agent-tower/coreWrote 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/skills/agent-tower/core/agent-tower-dev)<a href="https://agentmods.dev/skills/agent-tower/core/agent-tower-dev"><img src="https://agentmods.dev/badge/skills/agent-tower/core/agent-tower-dev/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/skills/agent-tower/core/agent-tower-dev"><img src="https://agentmods.dev/badge/skills/agent-tower/core/agent-tower-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01628 |
| Opus 5.5 | $0.00034 | $0.00651 |
| Sonnet 5.5 | $0.00017 | $0.00326 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
agent-tower-dev 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 24d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Tower 开发指南
工作流程
- 先看工作区状态和相关包的
package.json，按任务读取下列 reference；以真实实现和邻近测试为准，历史设计及CLAUDE.md可能落后于代码。 - 沿调用链检查 shared 类型、Prisma、Service/Route、Socket/MCP 和前端缓存。涉及执行时，另外区分 Task、Session、runtime turn、OS 进程和 TeamRun Invocation 的状态与所有者。
- 业务不变量放 Service；
SessionManager负责业务会话及持久化，RuntimeCoordinator协调 CLI/ACP Driver。AgentPipeline只是 CLI 的 PTY/解析子链路，不代表全部 Agent 执行。 - 沿用邻近错误响应、依赖注入和缓存模式；普通 Route 做输入及响应转换，已有特殊文件/代理 Route 不借局部需求统一重构。
- 先验证直接受影响的行为，再按跨包契约扩大检查。公开行为变化同步
packages/docs-site/docs/；专项设计和内部排障放顶层docs/。
仓库入口
| 范围 | 实际入口 |
|---|---|
| 共享契约 | packages/shared/src/types.ts、socket/events.ts、agent-runtime-support.ts、provider-capabilities.ts |
| 服务及 CLI | packages/server/src/cli.ts / index.ts 设置环境并同步 schema，app.ts 组合 HTTP、Socket、worker |
| Agent 执行 | packages/server/src/services/session-manager.ts、runtime/、pipeline/、executors/、output/ |
| 浏览器应用 | packages/web/src/routes/index.tsx、hooks/、lib/socket/、stores/ |
| 桌面及文档 | packages/desktop/src/main.ts、scripts/build-publish.mjs、packages/docs-site/ |
表中短路径沿用该行已标出的 src 目录，完整路径相对仓库根目录。shared 包对外导出指向 dist；Vitest 则将主要 shared import alias 到源码，因此测试通过不代表跨包构建已通过。
按需读取
- Route/Service、Prisma、任务读模型、Socket、MCP：backend-patterns.md
- Git workspace、后台服务、认证、preview、文件交付：workspace-security-patterns.md
- React、Query cache、Zustand、实时同步、i18n：frontend-patterns.md
- CLI/ACP runtime、Session、Provider、独立对话、Parser、新增 Agent：pipeline-patterns.md
- TeamRun、成员、消息、WorkRequest、Invocation、成员 workspace：teamrun-patterns.md
- Electron runtime、打包、公开文档站：desktop-docs-patterns.md
必守边界
- 将跨端实体、状态和 Socket payload 放在
@agent-tower/shared；server ESM import 保留.js后缀。 - Prisma 业务状态通常存为
String，由 shared enum/union 约束；JSON string 在 Service 边界转换。schema 同步不等于历史数据迁移。 - 实时变更同时检查
EventMap、shared Socket contract、SocketGateway和前端重连/缓存失效；Socket 通知不能代替 REST 恢复。 - 保留 browser、internal、Agent credential 的身份区分，以及 tunnel/access/Socket auth、CSRF、local-only 和 preview loopback 边界。
- 同时支持
WORKTREE与MAIN_DIRECTORY；不要假设每个项目都是 Git 仓库或每个任务只有一个 workspace。 - 使用根
package.json固定的 pnpm 版本；新增带安装脚本的依赖时先审核脚本，再在pnpm-workspace.yaml的allowBuilds中明确设为true或false。 - runtime 逻辑完成、连接关闭和整棵进程树清理是不同事实；未确认清理前不释放可重用资源或宣称停止成功。
- 列表热路径使用 preview/truncated DTO；完整 task/message 正文按需加载。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed · +16 lines · -16 tokens per session aba736d8a5ad
- 2mo ago First seen · 57 lines · 100 tokens per session scan A 234158cd857b
agent-tower-dev is a skill published in the GitHub repository agent-tower/core (397 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 1,628 once invoked, about $0.0003 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.
agent-tower-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-tower-devagent-tower/core | Skill | 397 | yesterday | Apache-2.0 | A | 84 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |