agent-swarm-workflow

# Agent Swarm Workflow — Parallel Implementation

> **Core Insight:** Every agent is fungible and a generalist. They all use the same base model and read the same AGENTS.md. Simply telling one it's a "frontend agent" doesn't make it better at frontend.
>
> The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.

---

## Prerequisites

Before starting a swarm:

1. **Comprehensive plan** created (see `planning-workflow` skill)
2. **Polished beads** ready (see `beads-workflow` skill)
3. **AGENTS.md** configured with all tool blurbs
4. **Agent Mail server** running (`am` or `~/projects/mcp_agent_mail/scripts/run_server_with_token.sh`)
5. **NTM** available for session management

---

## The Swarm Architecture

```
┌─────────────────────────────────────────────────────────────┐
│                         BEADS                               │
│     (Task graph with dependencies, priorities, status)      │
└─────────────────────────────────────────────────────────────┘
                              │
                    ┌─────────┴─────────┐
                    ▼                   ▼
┌─────────────────────────────┐  ┌─────────────────────────┐
│        BV                   │  │     AGENT MAIL          │
│  (What to work on)          │  │  (Coordination layer)   │
└─────────────────────────────┘  └─────────────────────────┘
         │                            │
         └──────────────┬─────────────┘
                        ▼
┌─────────────────────────────────────────────────────────────┐
│                    NTM + AGENTS                             │
│  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐     │
│  │ CC  │  │ CC  │  │ Cod │  │ Gmi │  │ CC  │  │ Cod │     │
│  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘     │
└─────────────────────────────────────────────────────────────┘
```

---

## Starting the Swarm

### Using NTM (Named Tmux Manager)

```bash
# Spawn a swarm with multiple agents
ntm spawn myproject --cc=3 --cod=2 --g...