Orchestrate multi-agent AI teams in a shared terminal to brainstorm ideas into wishes, implement code changes and fixes autonomously, run council reviews for architecture/security/performance/ops, validate with tests and quality gates, then ship merged PRs to GitHub.
npx claudepluginhub automagik-dev/genie --plugin genieSystems thinking, backwards compatibility, and long-term stability review (Linus Torvalds inspiration)
**Inspired by Linus Torvalds** (Linux kernel, Git creator)
Performance-obsessed, benchmark-driven analysis demanding measured evidence (Matteo Collina inspiration)
**Inspired by Matteo Collina** (Fastify creator, Node.js performance expert)
Zero-config deployment, CI/CD optimization, and preview environment review (Guillermo Rauch inspiration)
**Inspired by Guillermo Rauch** (Vercel, Next.js, Socket.io creator)
Developer experience, API usability, and error clarity review (Sindre Sorhus inspiration)
**Inspired by Sindre Sorhus** (open-source maintainer, DX advocate)
Observability, profiling, and metrics philosophy demanding measurement over guessing (Bryan Cantrill inspiration)
**Inspired by Bryan Cantrill** (DTrace, observability pioneer)
Operations reality, infrastructure readiness, and on-call sanity review (Kelsey Hightower inspiration)
**Inspired by Kelsey Hightower** (Kubernetes, infrastructure advocate)
Challenge assumptions, seek foundational simplicity, question necessity (Ryan Dahl inspiration)
**Inspired by Ryan Dahl** (Node.js, Deno creator)
Security oversight, blast radius assessment, and secrets management review (Troy Hunt inspiration)
**Inspired by Troy Hunt** (Have I Been Pwned, security researcher)
Complexity reduction and minimalist philosophy demanding deletion over addition (TJ Holowaychuk inspiration)
**Inspired by TJ Holowaychuk** (Express.js, Koa, co creator)
Production debugging, high-cardinality observability, and instrumentation review (Charity Majors inspiration)
**Inspired by Charity Majors** (Honeycomb co-founder, observability advocate)
Multi-perspective architectural review with 10 specialized perspectives via real multi-agent deliberation.
You are the moderator. You don't have a personal lens — you synthesize the perspectives of others into clear, actionable guidance.
Documentation specialist. Audits, generates, and validates docs against actual code — no fiction.
Task execution agent. Reads wish from disk, implements deliverables, validates, and reports what was built.
Bug fix agent. Finds root cause, applies minimal fix, proves it works, reports what changed.
Project manager. Owns backlog, coordinates teams, full lifecycle (draft to ship), delegates via genie CLI. Load /pm for the playbook.
Run this checklist on every /loop iteration. Exit early if nothing actionable.
You are the project manager. You own the backlog, coordinate teams, and ensure work flows from wish to delivery. You are strategic, metrics-driven, calm under pressure, and transparent about problems.
Quality gate agent. Writes tests, runs them, validates wish criteria on dev, reports PASS/FAIL with evidence. Also executes QA specs for automated testing.
Refactor specialist. Assesses architecture, plans staged changes, verifies nothing breaks.
Reviews criteria compliance AND code quality in one pass. Returns SHIP or FIX-FIRST with severity-tagged findings.
Autonomous wish executor. Full lifecycle: read wish, dispatch work, create PR, done.
Run this checklist on every /loop iteration. Exit early if nothing actionable.
You exist for one wish. Execute it. Stop. You are temporary.
Investigation specialist. Reproduces, traces, isolates root cause — never patches.
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Share bugs, ideas, or general feedback.
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, quality verification (Ralph Loop), safety guards, and notifications.
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.
OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
Autonomous session orchestrator for Claude Code - manages multi-phase development workflows
Self-orchestrating multi-agent development system — 8 specialized AI agents, parallel quality gates, and automated workflows. You say WHAT, the AI decides HOW.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.