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

SKILL

claude-devfleet

Plan and orchestrate parallel coding agents with progress tracking and reports.

Stars

★ 244,048

Source

GitHub

Updated

2026-08-29

// securityLow risk

Prompt only, no code
Open source
Community-trusted· 244.0k

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "claude-devfleet" skill from askskill:
1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/claude-devfleet/SKILL.md
2. Save it as ~/.claude/skills/claude-devfleet/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Break down and execute a backend project

Prompt

Use DevFleet to plan a project for “build a REST API with auth and tests.” Show me the mission DAG and dependencies first; after I approve, dispatch the first mission, report status periodically, and finish with a structured summary report.

Expected

A project plan, mission dependency chain, progress updates, and a final report with changed files, completed work, errors, and next steps.

Manually create and chain missions

Prompt

Help me create a project manually: create the project, then add two missions—“implement login API” and “add unit tests”—make the second depend on the first with auto-dispatch enabled; then start the first mission and monitor progress.

Expected

Project and mission details, agents started in dependency order, plus mission status updates and a final result summary.

Review the global mission dashboard

Prompt

Get the DevFleet dashboard and summarize running agents, system stats, and recent activity, including which missions are in progress and which are complete.

Expected

A system overview summarizing running agents, mission progress, and recent activity.

// use cases

Run multi-step development work in parallel

Developers working on coding projects with multiple dependent stages can generate a mission DAG first, then let multiple agents execute in isolated worktrees. This makes dependencies and parallel progress easier to manage.

Monitor agent execution and collect reports

For long-running missions, users can poll mission status or review the dashboard instead of blocking the conversation. When a mission finishes, they can read a structured report covering changed files, completed work, errors, and next steps.

Manually orchestrate dependency chains

If you do not want automatic project planning, you can manually create projects and missions, then set depends_on and auto_dispatch. This suits teams that want explicit control over task breakdown and execution order.

// docs

AI summary

The documentation explains how Claude DevFleet orchestrates multiple coding agents in parallel, with each agent running in an isolated git worktree. It covers when to use the system, how to install and connect the separate DevFleet server over MCP, and the standard workflow from planning and dispatching to monitoring and reporting. It also summarizes core tools such as plan_project, dispatch_mission, get_mission_status, get_report, and get_dashboard.

Show full docs ▾

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).

…

View full docs ↗

// FAQ

What does this skill do?

It orchestrates multiple Claude Code agents to work on coding tasks in parallel. It supports project planning, mission dispatching, progress monitoring, and reading structured execution reports.

What setup is required before using it?

You need to install and run the separate DevFleet server first, then connect to the running instance via MCP. The docs show a local setup on port 18801 and recommend verifying that the process on that port is the DevFleet binary you installed.

How should long-running missions be monitored?

The docs suggest using get_mission_status polling or get_dashboard instead of blocking the conversation with a long wait_for_mission call. That way, users can keep seeing progress updates.