gran-maestro
01Plugin Claude Code
An AI-agent coordination add-on for project managers who direct several coding agents instead of writing code themselves.
Plugin Claude Code
An AI-agent coordination add-on for project managers who direct several coding agents instead of writing code themselves.
Plugin Claude Code
An AI-agent coordination add-on for project managers who direct several coding agents instead of writing code themselves.
Instructions file CodexOpenCode
Project instructions for Gran Maestro, a plugin that manages project hooks and related development rules. Hooks are scripts that run automatically at events such as starting or ending a session.
Instructions file
Project instructions for Gran Maestro, including its documentation, release process, and rules for managing command hooks. Hooks are scripts that run automatically at defined points in an agent workflow.
Agent
An architecture-design agent for an analysis team. It plans system structure, APIs, module boundaries, and the direction of dependencies between components.
Agent
A template for turning several review reports into one precise feedback document for an outside coding agent.
Agent
A prompt template for sending a planned coding task to an outside agent such as Codex, AGY, or Claude. It includes the task context and checks expected before completion.
Agent
The coordinating agent for Gran Maestro, a system that plans and reviews coding work. It leads requirement analysis and review while leaving implementation to other agents.
Agent
A database planning template for defining data models, table relationships, field rules, indexes, and migration plans. It produces design documents rather than implementation code.
Agent
A UI planning template for designing screens, reusable components, user interactions, and design-system use. It produces written specifications rather than implementation code.
Hook
Runs when a session starts, executing mst-session-init.sh. From myrtlepn/gran-maestro.
Hook
Runs before the agent uses a tool for Skill and ScheduleWakeup tool calls, executing mst-pre-tool-use.sh (2 commands). From myrtlepn/gran-maestro.
Hook
Runs when the agent finishes a response, executing mst-stop-hook.sh. From myrtlepn/gran-maestro.
Hook
Runs when you submit a prompt, before the agent sees it, executing mst-auto-chain-context.sh. From myrtlepn/gran-maestro.
Skill Claude CodeCodex
Internal shared include material for Gran Maestro skills. This is not a user-invocable workflow.
Skill Claude CodeCodex
A command for accepting work in the MST or Gran Maestro agent-coordination system, available only when explicitly invoked.
Skill Claude CodeCodex
A planning workflow for the Maestro system's agile-plan command. It runs only when that command or the Maestro system is explicitly requested.
Skill Claude CodeCodex
A narrowly controlled workflow for agile tasks in the MST, Gran Maestro, or Maestro system. Agile is a way of organizing software work into small, iterative tasks.
Skill Claude CodeCodex
A specialized command for the agy function of MST, Gran Maestro, or Maestro, used only when that function is explicitly requested.
Skill Claude CodeCodex
A controlled approval workflow for the MST, Gran Maestro, or Maestro system. It runs only when the approval command is explicitly requested.
Skill Claude CodeCodex
A controlled archive workflow for the MST, Gran Maestro, or Maestro system. It runs only when the archive command is explicitly requested.
Skill Claude CodeCodex
A cancellation command for MST, also called Gran Maestro or Maestro, a workflow system with explicit commands for managing sessions and delegated work.
Skill Claude CodeCodex
A narrowly scoped command for Maestro, a multi-step task system, that handles requests explicitly directed to its Claude function. It only runs when the user invokes the exact command or clearly asks to use that function.
Skill Claude CodeCodex
A cleanup workflow that runs only when explicitly called with the MST cleanup command or requested as part of Maestro. Its full behavior is not described here.