管理器 Getting Star
- 作者仓库星标 0
- 作者仓库 skills-registry
What Manager Is
A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. It routes tasks to Claude Code, Codex, Gemini CLI, and GPT, with parallel execution, workflow chaining, and learned routing patterns.
| Category | Key Tools | What It Does |
|---|---|---|
| Task lifecycle | task_submit, task_status, task_output, task_poll, task_list | Submit, monitor, and retrieve AI task results |
| Routing | task_route, task_decompose, task_explain | Smart backend selection and task breakdown |
| Parallel | task_run_parallel | Concurrent multi-backend execution with dependencies |
| Workflows | workflow_run | Multi-step chains with retry and escalation |
| Templates | template_save, template_list, template_run | Reusable workflow patterns |
| Sessions | session_start, session_send, session_list | Interactive AI sessions |
| Direct access | codex_exec, codex_review, gemini_direct | Call specific backends directly |
| Analytics | get_analytics, run_analyzer | Execution stats and pattern analysis |
| Loaves | create_loaf, loaf_update, loaf_status, loaf_close | Multi-step tracked jobs |
| Notifications | notify | Desktop notifications for task events |
Key Tools
| I want to... | Use |
|---|---|
| Delegate a coding task | task_submit(backend="claude_code", prompt="...") |
| Let Manager pick the best AI | task_submit(auto_route=true, prompt="...") |
| Run tasks in parallel | task_run_parallel(steps=[...]) |
| Chain steps with retry | workflow_run(steps=[...]) |
| Save a reusable pattern | template_save(name="...", steps=[...]) |
| Check what backend to use | task_route(prompt="...") |
| Start interactive session | session_start(backend="claude_code") |
| Get execution stats | get_analytics |
Common Patterns
Quick delegation: manager:task_submit(backend="claude_code", prompt="Add error handling to src/main.rs", working_dir="C:/project")
Poll for completion: manager:task_poll(task_id="abc-123", timeout=60)
Parallel review: manager:task_run_parallel(steps=[ {id: "frontend", backend: "claude_code", prompt: "Review src/ui/", parallel_group: "review"}, {id: "backend", backend: "codex", prompt: "Review src/api/", parallel_group: "review"} ])
Anti-Patterns
- Don't poll in a tight loop — use task_poll with a timeout instead of repeated task_status
- Don't hardcode backends — use auto_route or task_route to let Manager learn which backend works best
<!-- tomevault:4.0:skill_md:2026-05-23 -->Source: AIWander/manager — distributed by TomeVault.
- 流狐分类
- 通用
- 作者声明 Agent
- 未找到明确声明；不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描，不代表运行安全
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 需简单配置
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无（仅作为资料）
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. It routes tasks to Claude Code, Codex, Gemini CLI, and GPT, with parallel execution, workflow chaining, and learned routing patterns. Category · Key Tools · What It Does
I want to... · Use Delegate a coding task · tasksubmit(backend="claudecode", prompt="...") Let Manager pick the best AI · tasksubmit(autoroute=true, prompt="...")
Quick delegation: manager:tasksubmit(backend="claudecode", prompt="Add error handling to src/main.rs", workingdir="C:/project") Poll for completion:
Don't poll in a tight loop — use taskpoll with a timeout instead of repeated taskstatus Don't hardcode backends — use autoroute or taskroute to let Manager learn which backend works best Source: AIWander/manager — distributed by TomeVault.
## What Manager Is
A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. It routes tasks to Claude Code, Codex, Gemini CLI, and GPT, with parallel execution, workflow chaining, and learned routing patterns.
| Category | Key Tools | What It Does |
|----------|-----------|-------------|
| Task lifecycle | task_submit, task_status, task_output, task_poll, task_list | Submit, monitor, and retrieve AI task results |
| Routing | task_route, task_decompose, task_explain | Smart backend selection and task breakdown |
| Parallel | task_run_parallel | Concurrent multi-backend execution with dependencies |
| Workflows | workflow_run | Multi-step chains with retry and escalation |
| Templates | template_save, template_list, template_run | Reusable workflow patterns |
| Sessions | session_start, session_send, session_list | Interactive AI sessions |
| Direct access | codex_exec, codex_review, gemini_direct | Call specific backends directly |
| Analytics | get_analytics, run_analyzer | Execution stats and pattern analysis |
| Loaves | create_loaf, loaf_update, loaf_status, loaf_close | Multi-step tracked jobs |
| Notifications | notify | Desktop notifications for task events |
## Key Tools
| I want to... | Use |
|--------------|-----|
| Delegate a coding task | task_submit(backend="claude_code", prompt="...") |
| Let Manager pick the best AI | task_submit(auto_route=true, prompt="...") |
| Run tasks in parallel | task_run_parallel(steps=[...]) |
| Chain steps with retry | workflow_run(steps=[...]) |
| Save a reusable pattern | template_save(name="...", steps=[...]) |
| Check what backend to use | task_route(prompt="...") |
| Start interactive session | session_start(backend="claude_code") |
| Get execution stats | get_analytics |
## Common Patterns
…作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。
章节 -> What Manager Is → Key Tools → Common Patterns → Anti-Patterns
要点 -> Quick delegation · Poll for completion · Parallel review · A single MCP server (manager.exe) with 48 tools for multi-AI orchestration. · | I want to... · --- > Source: [AIWander/manager](https://github.com/AIWander/manager) — distributed by [TomeVault](https://tomevault.io).
文件/命令 -> src/main.rs · src/ui · src/api · AIWander/manager · github.com/AIWander/manager
内容 SHA-256 -> b23e07f832e3
原文结构
适用与边界
原文中的明确线索
src/main.rs、src/ui、src/api、AIWander/manager、github.com/AIWander/manager