Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By markus41
Orchestrate multi-agent teams and autonomous coding workflows in Claude Code using expert skills, commands, and agents that automate project bootstrapping, tech stack fingerprinting, LSP installs, hook deployments, MCP server management, CI/CD integrations, security hardening, context optimization, and performance profiling for enterprise-scale development.
npx claudepluginhub markus41/claude --plugin claude-code-expertCreate and manage custom agents for Claude Code.
Deploy a first-class autonomy operating profile that composes memory, workflow, orchestration, hooks, and verification into one deployable system. More than documentation — generates preset files, enforcement hooks, and specialized agents.
Scan an existing repository, detect its full tech stack, and generate a deployable
Use `/cc-budget` to understand how much of your context window is consumed by always-on content (CLAUDE.md, rules, skills, MCP schemas) and how much remains for actual work.
Bootstrap Claude Code channel integrations for your project: generate starter server
Manages sub-agent lifecycle — health checks, idle detection, cleanup, retention, and escalation. Ensures no orphaned or stalled agents waste tokens.
Second-round audit agent that reviews work produced by other agents. Finds gaps, missed edge cases, inconsistencies, and quality issues that first-pass agents missed. Uses Context7 to validate library usage against official docs.
Decomposes any engineering task into a phased, risk-assessed plan with explicit verification steps and rollback paths. Invoked by /cc-autonomy plan "<task>". Writes the plan to .claude/active-task.md. Never implements — plan-only.
Final review agent for autonomous work. Reads the plan from .claude/active-task.md, diffs changed files against the plan, reads each changed file, and issues BLOCK or APPROVE with specific findings. Invoked by /cc-autonomy review after the verifier passes. Never modifies files.
Runs the verification suite after an implementation phase completes. Reads verification steps from .claude/active-task.md, detects project type, runs typecheck + lint + tests + diff check + secret scan, and produces a structured PASS or FAIL report. Never modifies files.
Complete guide to managing sub-agent and teammate lifecycle in Claude Code — health checks, idle detection, cleanup, retention, and the mandatory audit loop.
Complete guide to the Claude Agent SDK for building custom AI agents.
Agent-team topology kits — 5 production-ready team configurations with task decomposition, file ownership, worktree guidance, and quality-gate hooks
Advanced patterns for Claude Code Agent Teams — topology design, cross-team communication, worktree coordination, failure handling, and cost management
> Orchestrate teams of Claude Code sessions working together with shared tasks, inter-agent messaging, and centralized management.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Enterprise development toolkit for teams - DevOps, code quality, integrations, workflow automation, documentation, and performance optimization across multi-cloud and full-stack platforms
Use this agent for optimizing human-agent collaboration workflows and analyzing workflow efficiency. This agent specializes in identifying bottlenecks, streamlining processes, and ensuring smooth handoffs between human creativity and AI assistance. Examples:\n\n<example>\nContext: Improving development workflow efficiency
Multi-agent orchestration system with MCP tools and Claude Code plugin agents. 51 specialized agents for development workflows, code quality, deployment, research, and more.
Context management and multi-agent orchestration with performance optimization tools
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Agent orchestration harness for Claude Code — campaign persistence, fleet coordination, intent routing
AI-powered upgrade intelligence platform. Multi-agent council analyzes your codebase across 8 dimensions, produces confidence-scored suggestions with visual impact heatmaps, upgrade roadmaps, framework-specific deep dives, and before/after impact previews. Features innovation radar, tech debt forecasting, and coordinated upgrade bundles.
Enterprise development toolkit for teams - DevOps, code quality, integrations, workflow automation, documentation, and performance optimization across multi-cloud and full-stack platforms
Professional-grade multi-LLM agent coordination with comprehensive registry system, mandatory orchestration protocol, and production-ready DevOps workflows. Portable and customizable for any project.
Streamline development on the-lobbi/keycloak-alpha with Keycloak management, service orchestration, and test generation
The Conduit-Artisan Hybrid - AWS EKS deployments with Helm, Keycloak authentication, and Harness CI/CD. Combines pipeline excellence with developer velocity.
Share bugs, ideas, or general feedback.
A plugin-based AI agent orchestration platform that combines a visual workflow builder with a deep Claude Code configuration system. Fourteen domain plugins extend the platform across cloud infrastructure, enterprise SaaS, home automation, and more. The root plugin (claude-orchestration v4.0.1) ships 137 agents, 55 skills, and 100+ slash commands that activate automatically through a registry-backed keyword system.
The frontend (@accos/frontend v1.0.0) is the control surface: a React 18 application where you design, visualize, and manage multi-agent workflows and the plugin marketplace.
┌─────────────────────────────────────────────────────────────────┐
│ Visual Workflow Builder │
│ ReactFlow canvas · Zustand state · WebSocket │
└────────────────────────┬────────────────────────────────────────┘
│
┌────────────────────────▼────────────────────────────────────────┐
│ Plugin System Core │
│ Discovery · Installation · Validation · Dependency resolution │
│ Health checking · Sandboxing · Federated registry │
└───────────┬────────────────────────────────┬────────────────────┘
│ │
┌───────────▼──────────┐ ┌────────────▼───────────────────┐
│ 14 Domain Plugins │ │ Agent Fleet │
│ jira-orchestrator │ │ 137 agents · 30+ categories │
│ tvs-microsoft-deploy│ │ 55 skills · 100+ commands │
│ home-assistant-arch │ │ Activated via registry index │
│ fastapi-backend │ └────────────────────────────────┘
│ ... and 10 more │
└───────────┬──────────┘
│
┌───────────▼──────────────────────────────────────────────────────┐
│ MCP Servers │
│ deploy-intelligence · lessons-learned · project-metrics │
│ code-quality-gate · workflow-bridge · perplexity · firecrawl │
└──────────────────────────────────────────────────────────────────┘
Task toolPrerequisites: Node.js 18+, pnpm
# Install dependencies
pnpm install
# Start development server
pnpm dev
# Opens at http://localhost:5173
# Build for production
pnpm build