Agent Army

A 2-layer parallel execution framework. Each Layer 1 agent has its own full context window (not a slice). Each spawns Layer 2 sub-agents under it. The result is many independent brains running at once — not one brain divided.

Commander (you)
 |
 |-- Layer 1: Team (3 to 50+, each = own 1M context)
 |    |-- Agent A (1M) -- Sub-agent A1, A2, ...
 |    |-- Agent B (1M) -- Sub-agent B1, B2, ...
 |    |-- Agent C (1M) -- Sub-agent C1, C2, ...
 |    |-- ... (no cap)

Swarm vs. army: A swarm splits one context window across sub-agents — one brain, divided. An army gives each Layer 1 member its own window. That difference is the whole point of this skill.

When to use