By adilbilal
Full-stack autonomous development orchestrator with kanban integration (Asana, Jira, Linear, GitHub), second brain (Obsidian, Notion), and session memory. Build features with /maestro, build entire products with /maestro opus. Three-layer orchestration with self-improving agents, context management, and cost tracking.
Health check and diagnostics for Maestro installation
View and manage stories as a text-based kanban board
Second brain operations -- connect, search, save, and manage your knowledge base
Interactive configuration editor for Maestro
Estimate token cost before building. Shows expected spend by model, story count, and complexity.
Laser-focused fix agent for self-heal phase. Given a specific error and the affected file, applies the minimal fix. T4 context tier — receives only the error, file, and fix pattern.
Senior developer agent that implements stories using TDD. Dispatched by dev-loop for each story. Reports status: DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, or BLOCKED.
Background agent for scheduled monitoring tasks. Runs health checks, processes notes, generates briefings. Dispatched by the scheduler skill.
Skeptical QA reviewer that validates story implementations against acceptance criteria. Read-only — never modifies code. Reports APPROVED or REJECTED with confidence-scored issues.
Research agent for competitive analysis and market research. Uses web search and Playwright for comprehensive intel.
Generate Mermaid diagrams and ASCII dashboards for story dependencies, architecture, roadmaps, and progress tracking.
Voice command mapping for Claude Code's native /voice mode. Maps spoken commands to Maestro operations with TTS-optimized responses.
Continuous project monitoring via CronCreate. Schedules periodic checks for tests, type errors, and performance regressions.
Auto-generate tests for story changes. Unit tests for functions, integration tests for APIs, component tests for UI.
Design or update technical architecture. Produces .maestro/architecture.md with tech stack decisions, data model, API design, component structure, and infrastructure map.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Full-Stack Autonomous Development Orchestrator for Claude Code
Build features with /maestro. Build entire products with /maestro opus. Track progress on your kanban board. Persist knowledge in your second brain.
Maestro is a Claude Code plugin that orchestrates autonomous software development across three layers: Vision and Strategy (product research, competitive analysis, market positioning), Tactics and Architecture (decomposition, dependency graphs, tech stack decisions), and Execution (implement, self-heal, QA review, git craft). Each layer delegates to purpose-built agents that receive exactly the context they need.
Maestro tracks token costs, learns from every session, and progressively earns your trust through demonstrated reliability. It integrates with your existing tools — Asana, Jira, Linear, GitHub Issues for project management, and Obsidian or Notion as a persistent knowledge base.
# Install the plugin
claude plugin install maestro
# Initialize for your project
/maestro init
# Build a feature
/maestro "Add user authentication with email/password"
# Build an entire product
/maestro opus "Personal finance dashboard with budget tracking"
| Command | Description |
|---|---|
/maestro "task" | Build a feature autonomously |
/maestro opus "vision" | Build an entire product (Magnum Opus) |
/maestro init | Initialize for this project |
/maestro status | View progress, resume, pause, abort |
/maestro model | View/change model assignments |
/maestro help [topic] | Contextual help and FAQ |
/maestro doctor | Health check and diagnostics |
/maestro config | View/edit configuration |
/maestro board | Kanban board view |
/maestro brain | Second brain operations |
/maestro history | Past sessions and cost analysis |
/maestro plan "task" | Deep planning with codebase exploration |
/maestro notify | Push notifications (Slack, Discord, Telegram) |
/maestro viz | Visual dashboards and Mermaid diagrams |
/maestro demo | Interactive demo — learn how Maestro works |
/maestro quick-start | Pick from pre-built task templates |
User Request
|
v
[Classifier] --> routes to the right layer
|
+---> Layer 1: Vision & Strategy
| research, strategy, opus-loop
|
+---> Layer 2: Tactics & Architecture
| decompose, architecture, forecast
|
+---> Layer 3: Execution
dev-loop, git-craft, ship, preview
For each story in dependency order:
VALIDATE > DELEGATE > IMPLEMENT > SELF-HEAL > QA > GIT > CHECKPOINT
| Mode | Behavior |
|---|---|
--yolo | Auto-approve everything, maximum speed |
--checkpoint | Pause after each story for review (default) |
--careful | Pause after each phase for granular control |
Build entire products with /maestro opus "vision".
Sync stories with your project management tool. Stories appear as cards, status updates flow bidirectionally.
/maestro config set integrations.kanban.provider github
/maestro board
| Provider | Setup |
|---|---|
| GitHub Issues | gh CLI (no extra setup) |
| Asana | Asana MCP Server |
| Jira | Atlassian MCP Server |
| Linear | Linear MCP Server |
Persist decisions, learnings, and session summaries across sessions.
/maestro brain connect
/maestro brain search "authentication"
/maestro brain tldr
| Provider | Setup |
|---|---|
| Obsidian | Enable CLI in Obsidian Settings |
| Notion | Notion MCP Server |
/maestro doctor
Checks: core files, config, trust metrics, git status, hooks, MCP servers, integrations.
Maestro tracks reliability and adapts behavior:
| Level | Requirement |
|---|---|
| Novice | < 5 stories |
| Apprentice | 5-15 stories, > 60% QA first-pass |
| Journeyman | 15-30 stories, > 75% QA rate |
| Expert | 30+ stories, > 85% QA rate |
Cron-like daemon that runs Claude prompts on a schedule
npx claudepluginhub adilbilal/maestro-opusIntelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.