execute

Execute approved Maestro implementation plans across supported runtimes with session state management.

453|34|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/josstei/maestro-orchestrate --skill execute-josstei
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: execute
Source: https://github.com/josstei/maestro-orchestrate/tree/main/plugins/maestro/skills/execute
Command: npx skills add https://github.com/josstei/maestro-orchestrate --skill execute-josstei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually tracking and executing multi-phase implementation plans for Maestro projects is error-prone and time-consuming, especially when managing persistent session state, coordinating child agent delegation, and validating phase completion across complex development workflows.

Core Features & Use Cases

  • End-to-End Plan Execution: Reads approved implementation plans, resolves execution mode gates, and manages session state to run plans from start to finish.
  • Multi-Agent Coordination: Delegates phase work to specialized child agents and validates progress against the loaded Maestro methodology.
  • Cross-Runtime Compatibility: Works across all Maestro-supported runtimes (Gemini CLI, Claude Code, Codex, Qwen Code) with fallback to direct file operations if MCP tools are unavailable.
  • Use Case: A development team with an approved plan for a new authentication feature can use this skill to automatically execute all 4 standard workflow phases, track session state, and coordinate specialist agents for implementation, testing, and review without manual progress tracking.

Quick Start

Use the execute skill to run the approved implementation plan located at the user-provided path or the most recent plan in the docs/maestro/plans/ directory.

Frequently Asked Questions about execute

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute a multi-phase implementation plan end-to-end without manual tracking?

To execute approved implementation plans end-to-end, you can use automated session state management and child agent delegation to run the 4-phase Maestro workflow from start to finish without manual progress tracking.

Can I run Maestro implementation plans across different AI coding runtimes?

Yes, you can execute Maestro implementation plans across Gemini CLI, Claude Code, Codex, and Qwen Code runtimes using shared session-state contracts, with automatic fallback to direct file operations if MCP tools are unavailable.

What is the best way to coordinate child agents during phase execution?

The best way to coordinate child agents during phase execution is to load the Maestro methodology, delegate specialized phase work to child agents, and validate their progress against the standardized 4-phase workflow requirements.

How does session state management work for complex software development workflows?

Session state management for complex workflows works by resolving execution mode gates, reading approved plans, and maintaining persistent state across the 4-phase execution lifecycle to eliminate manual tracking errors.

Do I need MCP tooling to initialize workspaces and transition sessions?

MCP tooling is not strictly required to initialize workspaces and transition sessions; the execution skill automatically falls back to direct file operations to manage persistent state if MCP tools are unavailable.

When do I need automated phase execution for software development projects?

You need automated phase execution for medium and complex software development projects that require persistent session state, multi-agent delegation, and standardized validation across the 4-phase Maestro workflow.