By Lumantis
One prompt, full orchestration, zero intervention. 170+ specialized agents and 5 orchestration patterns for autonomous multi-agent pipelines.
The Agency works with GitHub Copilot out of the box. No conversion needed β
**SOURCE: https://github.com/msitarzewski/agency-agents**
Expert in cultural systems, rituals, kinship, belief systems, and ethnographic method β builds culturally coherent societies that feel lived-in rather than invented
Expert in physical and human geography, climate systems, cartography, and spatial analysis β builds geographically coherent worlds where terrain, climate, resources, and settlement patterns make scientific sense
Expert in historical analysis, periodization, material culture, and historiography β validates historical coherence and enriches settings with authentic period detail grounded in primary and secondary sources
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.
One prompt. Full orchestration. Zero intervention.
Generate complete, autonomous, self-healing multi-agent orchestrations
from a single natural language prompt.
Just. TRY. IT.
MegaBrain is a Claude Code plugin that transforms any project idea into a fully executable, multi-agent orchestration pipeline. You describe what you want to build, and MegaBrain creates a permanent skill that runs the entire project autonomously from start to finish.
You: /new-orchestration "Build a SaaS task manager with auth, dashboard, and Stripe billing"
Claude: Orchestration created: /lumantis-saas-task-manager
Phases: 12 | Agents: 34 | Pattern: dag-pipeline | Complexity: large
You: /lumantis-saas-task-manager
Claude: [runs autonomously to completion...]
Phase 1/12 complete - Project scaffolded
Phase 4/12 complete - API endpoints built, 47 tests passing
Phase 8/12 complete - Frontend integrated, visual validation passed
Phase 12/12 complete - Deployed. All 94 tests green.
COMPLETE - Final report below.
| Feature | Description |
|---|---|
| 170+ Specialized Agents | From Frontend Developer to Security Engineer to TikTok Strategist |
| 5 Orchestration Patterns | Sequential, Parallel Fan-Out, DAG Pipeline, Loop-Iterate, Hybrid |
| 100% Autonomous | Zero questions during execution. All decisions made automatically |
| Self-Healing | Tiered retry: same agent, alt approach, different agent, decompose |
| Auto-Dream Memory | 4-phase memory consolidation after every orchestration |
| Learning Loops | Instinct capture, agent performance tracking, meta-improvement |
| Resume & Recovery | Interrupted? Resume exactly where you left off |
| Visual Checkpoints | Screenshots via Claude Preview for UI validation |
| Scalable to 50+ agents | Mega projects decompose into sub-orchestrations |
Lumantis-MegaBrain folder into the app window/new-orchestration to start./new-orchestration "Create a portfolio website with dark mode, blog, and contact form"
MegaBrain will:
/lumantis-portfolio-site skillThen run it:
/lumantis-portfolio-site
Sit back. It runs to completion autonomously.
Your Prompt
|
v
[DECODE] -----> Intent Map (domains, complexity, tech stack)
|
v
[ARCHITECT] --> DAG Blueprint + Agent Roster + Quality Gates
|
v
[COMPOSE] ----> Complete /lumantis-* skill file
|
v
[REVIEW] -----> Adversarial verification (fix loop if needed)
|
v
[DEPLOY] -----> Installed in ~/.claude/skills/ and ready to use
| Prompt | Generated Skill | Agents Used |
|---|---|---|
| "Build a SaaS with auth and billing" | /lumantis-saas-auth-billing | Software Architect, Backend Architect, Frontend Dev, Security Engineer, DevOps... |
| "Marketing campaign for my app launch" | /lumantis-marketing-launch | Content Creator, SEO Specialist, Social Media Strategist, Growth Hacker... |
| "Security audit of my codebase" | /lumantis-security-audit | Security Engineer, Threat Detection, Code Reviewer, Compliance Auditor... |
| "Build a 2D platformer in Godot" | /lumantis-godot-platformer | Game Designer, Godot Gameplay Scripter, Level Designer, Game Audio... |
| "Research AI trends and write a report" | /lumantis-ai-research | Trend Researcher, AI Engineer, Technical Writer, Analytics Reporter... |
npx claudepluginhub lumantis/megabrainMission Planner, Agent Creator, Skill Creator, and Librarian β the complete Forge suite for science-backed AI team assembly
Multi-agent system optimization, agent improvement workflows, and context management
Autonomous Development Orchestrator - Transform ideas into production-ready applications through multi-agent pipeline. Spec β Plan β Tasks β 100% Working App.
Multi-agent orchestrator β supervisor loop that launches agents to implement plans
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
The team-architecture factory for Claude Code β a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Codeμ© ν μν€ν μ² ν©ν 리: λλ©μΈ ν λ¬Έμ₯μ μμ΄μ νΈ νκ³Ό μ€ν¬ μΈνΈλ‘ λ³ννλ λ©ν μ€ν¬.