Orchestrate agent-driven development workflows: convert raw ideas into structured missions with plans and blueprints, dispatch sub-agents for parallel task execution, enforce TDD via code scrutiny and user testing validations at checkpoints, manage progress and handoffs through CLI commands in .maestro projects.
npx claudepluginhub reinamaccredy/maestro --plugin maestroBase procedures for all mission agents: startup, cleanup, and handoff. REQUIRED skill for all mission feature implementations.
Generate visual HTML blueprint pages and structured plan specs for maestro project features. Explores the codebase, produces a `.md` plan in maestro format (Context, Critical Files, Design Decisions, Phases with Tasks and acceptance criteria) saved to `.maestro/plans/`, plus a visual HTML presentation. Use when the user asks to blueprint a maestro feature, plan an implementation for this project, or says "blueprint X" while working in the maestro codebase. Also use proactively for non-trivial maestro changes that span multiple files or architectural concerns.
Enter conductor mode: plan, decompose, and dispatch -- sub-agents implement, not you. Use when user says 'you orchestrate', 'conduct this', 'delegate this', 'don't code yourself', 'break this into sub-agents', 'run this milestone without doing it yourself', or wants to stay in the driver seat while you manage agents. Works for formal mission/milestone execution and ad-hoc decomposition.
Define and register custom skills for use in Mission Control missions. Create skill definitions with frontmatter, procedures, and validation rules.
Plan and structure new missions. Brainstorm raw ideas into decomposed missions with milestones, features, agent types, constraints, and the exact `maestro handoff` command for the first external agent.
Run code scrutiny validation during mission checkpoints. Spawns review subagents, synthesizes results, and produces validation reports.
Run user testing validation during mission checkpoints. Determines testable assertions, sets up test environment, spawns flow validators, and synthesizes results.
Collaboratively turn a rough idea into an approved design before planning or implementation. Use when the user wants to create a feature, change behavior, explore options, refine a fuzzy request, or decide what should be built before making a concrete plan. Inspect the current project context first, ask clarifying questions one at a time, propose 2 to 3 viable approaches with tradeoffs and a recommendation, then present a design and get user approval before handing off to maestro-plan.
Hand off current work to another session via `maestro handoff`. Covers transfer to a different agent (codex to claude or vice versa) AND transfer to another session of the same agent (claude to claude, codex to codex). Use when the user says "handoff", "hand off to codex/claude/new session", "drop a packet", "pickup handoff", "list open handoffs", or wants to pass work across any session boundary through maestro's native launcher.
Use for planned multi-step work at the mission level in any project that uses maestro. Covers mission lifecycle, feature/milestone navigation, feature prompt reading with injected memory, feature progress reporting, memory corrections, and agent-friendly mission-control TUI rendering. Use when the user says "show missions", "what feature am I on", "report feature progress", "read feature prompt", or when the agent needs to orient at the mission layer. Activates whenever a maestro-initialized project is detected.
Turn an approved brainstorm design into a concrete implementation plan by grounding on the real codebase or artifacts, consuming the accepted approach, constraints, assumptions, and unresolved decisions from the brainstorming phase, defining the done state, identifying risks and dependencies, sequencing phases and tasks, attaching validation to each step, and specifying the next executable move. In maestro projects, persists the plan to `.maestro/plans/<slug>.md` and emits task-batch JSON for `maestro-task`. Use when the user wants the phase after brainstorming, a phased approach, task breakdown, rollout sequence, implementation roadmap, or a concrete path from approved design to execution.
One-time QA installer for a repo. Scaffolds `.maestro/qa/` (config, sub-skills, sidecars, templates), symlinks `qa/` and per-app sub-skills into `.claude/skills/` and `.codex/skills/`, and optionally writes a GitHub Actions workflow. Use when the user runs `/maestro-qa`, says "install QA", "set up QA in this repo", or asks to bootstrap a project-local `/qa` runtime.
Set up a repository for Maestro-guided, human-in-the-loop agent work. Use when a project needs Maestro-owned context docs, evidence-first onboarding, root AGENTS.md guidance, language style guides, or a setup report before implementation work begins.
Use at the start of any multi-step work in any project that uses maestro, and throughout task execution. Decompose plans into `maestro task` entries before starting (including converting /maestro-plan or /planner output into a task batch), claim one task at a time, keep continuation state fresh, and close with a receipt. Agent auto-invokes without user action whenever a `.maestro/` directory is present in the current working tree or an ancestor.
Multi-agent development orchestration platform — 22 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Claude Code integration for MCP Task Orchestrator — schema-aware context, note-driven workflow
Structured, standards-aware development workflows for Claude Code
Skills for AI agent orchestration - memory search, code graph queries, documentation search, inter-agent messaging, and task planning
AI 오케스트라의 그랜드마스터 — PM이 코드를 쓰지 않고 AI 에이전트를 지휘하여 개발
24 commands, 8 agents. Loops, swarms, and teams powered by Claude Code's built-in Task System. Native task dependencies, ctrl+t progress, automatic persistence.