$ ~/registry/skill/affaan-m-claude-devfleet

SKILL

claude-devfleet

通过 Claude DevFleet 规划并调度多代理并行编码任务，跟踪进度并读取结构化报告。

星标

★ 284,897

来源

GitHub

更新于

2026-10-21

// 安全评估低风险

仅提示词，不执行代码
开源可审计
社区验证· 284.9k

正在进行安全审计…

凭证密钥
网络外发
代码执行
数据访问
来源供应链

// 安装

复制安装指令，让 AI 自动完成配置 · 推荐新手

请帮我安装 askskill 上的 "claude-devfleet" 技能：
1. 下载 https://raw.githubusercontent.com/affaan-m/ECC/main/skills/claude-devfleet/SKILL.md
2. 保存为 ~/.claude/skills/claude-devfleet/SKILL.md
3. 装好后重载技能，告诉我可以用了

// 下载

下载 SKILL.md机读安装清单 ↗

// 用法示例

拆解并执行后端项目

输入

请用 DevFleet 为“构建带鉴权和测试的 REST API”生成项目计划，先展示任务 DAG 和依赖关系；我确认后，调度首个 mission，并在执行过程中定期汇报状态，最后汇总结构化报告。

预期产出

项目计划、任务依赖链、执行状态更新，以及包含改动文件、完成内容、错误和后续步骤的报告。

手动创建并串联任务

输入

帮我手动创建一个项目：先建项目，再添加“实现登录接口”“补充单元测试”两个 mission，让第二个依赖第一个并自动调度；随后启动第一个任务并监控状态。

预期产出

返回项目与任务信息，按依赖顺序启动代理，并提供任务状态与最终结果摘要。

查看全局任务看板

输入

请获取 DevFleet dashboard，概览当前运行中的 agents、统计信息和最近活动，并指出哪些任务正在进行、哪些已完成。

预期产出

一份系统概览，说明运行中代理、任务进度和近期活动情况。

// 适用场景

并行推进多步开发任务

开发者在处理包含多个依赖阶段的编码项目时，可先生成任务 DAG，再让多个代理在隔离 worktree 中分阶段执行。这样能更清楚地管理依赖关系与并行进度。

监控代理执行与结果回报

当任务运行时间较长时，用户可以轮询任务状态或查看系统总览，而不是一直阻塞等待。任务完成后，可读取结构化报告了解改动文件、完成内容、错误与后续建议。

手动编排任务依赖链

如果不想直接自动规划项目，也可以手动创建项目与 mission，并设置 depends_on 与 auto_dispatch。适合对任务拆分和执行顺序有明确要求的团队。

// 文档

AI 摘要

文档介绍了 Claude DevFleet 的多代理编排流程，说明何时适合把编码任务拆分为并行 mission，并让代理在隔离的 git worktree 中执行。内容涵盖独立服务的安装与 MCP 连接方式、项目规划到调度再到监控与报告的标准工作流，以及 plan_project、dispatch_mission、get_report、get_dashboard 等核心工具的用途与使用建议。

展开完整文档 ▾

Claude DevFleet Multi-Agent Orchestration

When to Use

Use this skill when you need to dispatch multiple Claude Code agents to work on coding tasks in parallel. Each agent runs in an isolated git worktree with full tooling.

Setup

The DevFleet server is a separate project, not bundled with ECC. Install and run it from its repository first: https://github.com/LEC-AI/claude-devfleet

Then connect the running instance via MCP:

claude mcp add devfleet --transport http http://localhost:18801/mcp

Before first use, verify the process listening on port 18801 is the DevFleet binary you installed (see SECURITY.md on localhost MCP servers).

How It Works

User → "Build a REST API with auth and tests"
  ↓
plan_project(prompt) → project_id + mission DAG
  ↓
Show plan to user → get approval
  ↓
dispatch_mission(M1) → Agent 1 spawns in worktree
  ↓
M1 completes → auto-merge → auto-dispatch M2 (depends_on M1)
  ↓
M2 completes → auto-merge
  ↓
get_report(M2) → files_changed, what_done, errors, next_steps
  ↓
Report back to user

Tools

Tool	Purpose
`plan_project(prompt)`	AI breaks a description into a project with chained missions
`create_project(name, path?, description?)`	Create a project manually, returns `project_id`
`create_mission(project_id, title, prompt, depends_on?, auto_dispatch?)`	Add a mission. `depends_on` is a list of mission ID strings (e.g., `["abc-123"]`). Set `auto_dispatch=true` to auto-start when deps are met.
`dispatch_mission(mission_id, model?, max_turns?)`	Start an agent on a mission
`cancel_mission(mission_id)`	Stop a running agent
`wait_for_mission(mission_id, timeout_seconds?)`	Block until a mission completes (see note below)
`get_mission_status(mission_id)`	Check mission progress without blocking
`get_report(mission_id)`	Read structured report (files changed, tested, errors, next steps)
`get_dashboard()`	System overview: running agents, stats, recent activity
`list_projects()`	Browse all projects
`list_missions(project_id, status?)`	List missions in a project

Note on wait_for_mission: This blocks the conversation for up to timeout_seconds (default 600). For long-running missions, prefer polling with get_mission_status every 30–60 seconds instead, so the user sees progress updates.

Workflow: Plan → Dispatch → Monitor → Report

Plan: Call plan_project(prompt="...") → returns project_id + list of missions with depends_on chains and auto_dispatch=true.
Show plan: Present mission titles, types, and dependency chain to the user.
Dispatch: Call dispatch_mission(mission_id=<first_mission_id>) on the root mission (empty depends_on). Remaining missions auto-dispatch as their dependencies complete (because plan_project sets auto_dispatch=true on them).
Monitor: Call get_mission_status(mission_id=...) or get_dashboard() to check progress.
Report: Call get_report(mission_id=...) when missions complete. Share highlights with the user.

Concurrency

DevFleet runs up to 3 concurrent agents by default (configurable via DEVFLEET_MAX_AGENTS). When all slots are full, missions with auto_dispatch=true queue in the mission watcher and dispatch automatically as slots free up. Check get_dashboard() for current slot usage.

Examples

Full auto: plan and launch

plan_project(prompt="...") → shows plan with missions and dependencies.
Dispatch the first mission (the one with empty depends_on).
Remaining missions auto-dispatch as dependencies resolve (they have auto_dispatch=true).
Report back with project ID and mission count so the user knows what was launched.
Poll with get_mission_status or get_dashboard() periodically until all missions reach a terminal state (completed, failed, or cancelled).