By bluminal
[BETA] Teams-optimized orchestration for Synthex — sustained multi-agent collaboration via Claude Code Agent Teams. Requires the beta Agent Teams feature flag (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1). Depends on the Synthex plugin for agent definitions.
> **Internal development command -- not for end users.** This command is not registered in `plugin.json` (Decision D11). It exists solely to validate Agent Teams API assumptions before dependent implementation begins.
Execute implementation plan tasks using a persistent agent team instead of ephemeral subagent instances. This is the teams-optimized equivalent of Synthex's `next-priority` command.
Set up the Synthex+ teams plugin configuration for a project. This command scaffolds the configuration file needed for team-based orchestration commands. It checks for the Synthex dependency, verifies the experimental Agent Teams flag, detects orphaned team resources, and creates the project-level configuration.
Collaborative implementation planning using a persistent agent team instead of ephemeral subagent instances. This is the teams-optimized equivalent of Synthex's `write-implementation-plan` command.
Collaborative PRD refinement using a persistent agent team instead of ephemeral subagent instances. This is the teams-optimized equivalent of Synthex's `refine-requirements` command.
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.
A Claude Code plugin marketplace by Bluminal Labs.
LumenAI is a structured registry of Claude Code plugins — collections of AI agents and commands that work together to accomplish complex software delivery tasks.
/plugin marketplace add bluminal/lumenai
The first plugin in the marketplace. Synthex models a software startup's org chart as a collection of AI agents that synthesize to deliver complete, production-quality software.
/plugin install synthex
The organization spans the full software lifecycle: discover, build, ship, operate, and learn — with 15 agents organized into three layers and 11 commands that orchestrate them.
Orchestration Layer — Lead roles that coordinate specialists and drive execution.
| Agent | Role | Type |
|---|---|---|
| Tech Lead | Full-stack orchestrator, primary coding agent | Execution + Orchestration |
| Lead Frontend Engineer | Frontend tech lead, delegates to framework specialists | Execution + Delegation |
| Product Manager | Requirements gathering, implementation planning, product strategy | Planning + Strategy |
Specialist Layer — Domain experts invoked by leads or commands for focused work.
| Agent | Role | Type |
|---|---|---|
| Architect | System architecture guidance, ADRs, plan feasibility review | Advisory + Planning |
| Code Reviewer | Craftsmanship review, specification compliance, convention adherence | Advisory (PASS/WARN/FAIL) |
| Security Reviewer | Security review quality gate (vulnerabilities, secrets, access control) | Advisory (PASS/WARN/FAIL) |
| Terraform Plan Reviewer | Infrastructure-as-code review (cost, risk, security) | Advisory (PASS/WARN/FAIL) |
| Quality Engineer | Test strategy, coverage analysis, test writing | Execution + Advisory |
| Design System Agent | Design tokens, component governance, compliance audits | Execution + Advisory |
| Performance Engineer | Full-stack performance analysis (Core Web Vitals, queries, bundles) | Advisory |
| SRE Agent | SLOs/SLIs, observability, runbooks, blameless postmortems | Advisory + Execution |
| Technical Writer | API docs, user guides, migration guides, changelogs | Execution |
Research & Analysis Layer — Agents focused on understanding users, measuring outcomes, and driving improvement.
| Agent | Role | Type |
|---|---|---|
| UX Researcher | Research plans, personas, journey maps, Opportunity Solution Trees | Planning + Advisory |
| Metrics Analyst | DORA metrics, HEART/AARRR frameworks, OKR tracking | Advisory |
| Retrospective Facilitator | Structured retrospectives, improvement item tracking | Planning + Advisory |
| Command | Purpose | Agents Orchestrated |
|---|---|---|
| init | Initialize project configuration and directories | -- |
| next-priority | Execute next highest-priority tasks | Tech Lead |
| refine-requirements | Improve PRD clarity through multi-agent review | PM + Tech Lead + Lead Frontend Engineer |
| write-implementation-plan | Transform PRD into implementation plan | PM + Architect + Design System Agent + Tech Lead |
| review-code | Multi-perspective code review | Code Reviewer + Security Reviewer + Performance Engineer (opt.) |
| write-adr | Create Architecture Decision Record | Architect (interactive) |
| write-rfc | Create Request for Comments | Architect + PM + Tech Lead + Security Reviewer |
| test-coverage-analysis | Analyze test gaps, optionally write tests | Quality Engineer |
| design-system-audit | Audit frontend for design system compliance | Design System Agent |
| retrospective | Structured cycle retrospective | Metrics Analyst + Retrospective Facilitator |
| reliability-review | Operational readiness assessment | SRE Agent + Terraform Plan Reviewer (opt.) |
| performance-audit | Full-stack performance analysis | Performance Engineer |
A companion plugin to Synthex that adds persistent team orchestration via Claude Code's beta Agent Teams API. Synthex+ reuses Synthex agent definitions — it does not duplicate or modify them.
BETA — Requires the
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1feature flag. Both the Agent Teams API and this plugin are under active development.
/plugin install synthex-plus
Where standard Synthex spawns ephemeral subagents (each unaware of the others), Synthex+ creates persistent teams where agents share a task list, exchange messages via mailboxes, and coordinate autonomously.
npx claudepluginhub bluminal/lumenai --plugin synthex-plusOPNsense gateway intelligence plugin for EmberAI — firewall, routing, VPN, DNS, DHCP, IDS/IPS, and diagnostics via the OPNsense REST API
Cross-vendor network orchestration umbrella for EmberAI — unified topology, health, VLAN provisioning, security audits, and policy synchronization across vendor plugins
UniFi network intelligence plugin for EmberAI — topology discovery, health monitoring, WiFi analysis, client management, traffic inspection, security audit, and multi-site operations
AI agents modeled after a software startup org chart — specialized roles that synthesize to discover, build, ship, operate, and learn from complete, production-quality software.
Multi-agent team orchestration for parallel task execution, research, and implementation
Dynamically assemble expert agent teams for complex tasks using Claude Code's agent teams feature
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
General-purpose agent superteam for Claude code - contract-gated verification loops with 7 outer-loop roles, 5-phase orchestration, task form-driven inner-loop cooperation, and structural prevention of premature exits.
AI team orchestration. Give Claude Code an AI team — CTO, Engineer, QA, Designer work together while you watch.
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams