work-superspeedlisted

# Superspeed Fan a task out across real parallel sessions, reconcile it warm, and leave a log that says how to do it better next time. ## Read this before using it The advantage is real but narrow, and it was measured rather than assumed. On 2026-08-06, Claude Code 2.1.220, Apple M2 8-core, Max plan, four configurations and fourteen reps: | | one session, 4 subagents | one session, 4 teammates | **4 parallel `claude -p`** | |---|---:|---:|---:| | trivial task, 1 round | 52s | 59s | **22s** | | real task, 1 round | 64s | 59s | **31s** | | trivial, 3 rounds | 111s | 121s | **75s** | Separate sessions won every configuration and every individual rep, at identical correctness (24/24). **The mechanism is a fixed ~33s, not a multiplier.** The gap was 30s at one round and 36s at three, so it is a one-time orchestration toll, not something that compounds. That makes it 2.4x on a 22-second job and under 1% on an hour-long one. **So the honest rule: use this when a task splits into pieces that can run at once. Do not use it hoping to make one long serial task faster.** If the work does not divide, nothing here helps, and Anthropic's own 16-agent C-compiler run is the cautionary case: on an indivisible task every agent hit the same bug and overwrote the others. **Why separate sessions and not subagents.** Every in-session primitive is capped: subagents at 20 concurrent (10 in these settings), dynamic workflows at 16 and lower on machines with few cores. Separately launched sessi