bmad-party-mode

Spawn 2-4 BMAD subagents for roundtable discussions with a live roster.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/Wizarck/iguanatrader --skill bmad-party-mode-wizarck
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-party-mode
Source: https://github.com/Wizarck/iguanatrader/tree/main/skills/bmad-party-mode
Command: npx skills add https://github.com/Wizarck/iguanatrader --skill bmad-party-mode-wizarck

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates group discussions between BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.

Core Features & Use Cases

  • Spawns 2-4 BMAD subagents per discussion, each operating with its own persona and context.
  • Presents a live roster of agents with icons, roles, and principles, enabling informed choice of voices.
  • Supports optional --model and --solo modes, and loads project context to tailor responses.
  • Use case: run a roundtable on a complex project where diverse viewpoints improve outcomes.

Quick Start

Activate party mode to spawn 2-4 BMAD subagents, load the roster, and start a guided roundtable discussion with the user.

Frequently Asked Questions about bmad-party-mode

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate a multi-agent roundtable discussion for project planning?

Multi-agent roundtable orchestration spawns 2-4 independent subagents with distinct personas to discuss your project. It loads project context, presents an agent roster, and guides a collaborative discussion to improve planning and architecture decisions.

What is multi-agent orchestration and when do I need it for architecture reviews?

Multi-agent orchestration coordinates independent subagents to provide diverse viewpoints in a roundtable format. You need it for architecture reviews and collaborative brainstorming when multiple perspectives improve decision-making outcomes.

Can I run a single-agent session instead of a full group discussion?

Yes, you can run a single-agent session using the optional --solo mode. This bypasses the standard 2-4 subagent spawning process to focus on one perspective while still utilizing the loaded project context.

Do I need to manually configure subagent roles before starting a group brainstorming session?

No, manual subagent configuration is unnecessary. Agent roles are automatically derived from a manifest, and the system presents a live roster with icons, roles, and principles for your informed selection during brainstorming.

Can I specify different AI models for the subagents in a multi-agent conversation?

Yes, you can specify models for the subagents using the optional --model mode. This allows you to tailor the independent thinking and diverse perspectives within the multi-agent conversation.

What are the limitations of using subagents for collaborative brainstorming?

A key limitation is that the deterministic core loop avoids self-response, meaning subagents cannot reply to each other autonomously. Discussions are bounded by the 2-4 spawned agents and the loaded project context.