What problem does it solve? Coordinating multiple coding tasks manually is slow and error-prone. This Skill lets you plan a project, dispatch parallel Claude Code agents in isolated git worktrees, monitor their progress, and read structured completion reports through a running Claude DevFleet instance. ## Core Features & Use Cases - AI Project Planning: Use plan_project to break a natural-language description into a project with chained missions and dependency DAGs. - Parallel Agent Dispatch: Run up to 3 concurrent agents (configurable) with automatic dispatch as dependencies complete and auto-merge on success. - Monitoring & Reporting: Track progress with get_mission_status and get_dashboard, then read structured reports with files changed, errors, and next steps via get_report. - Use Case: Ask to build a REST API with auth and tests; the Skill plans the missions, dispatches the root mission, auto-dispatch chains the rest, and reports results for each completed mission. ## Quick Start Connect the DevFleet MCP server with claude mcp add devfleet --transport http http://localhost:18801/mcp, then ask the assistant to plan and launch your project, for example: plan and build a REST API with authentication and tests using DevFleet.
