Opus 5.5 background task: 168 agents, 2.8M tokens in a single 3.5-hour workflow
imjustnewatai · x · 2026-10-24
A user shared a screenshot of an Opus 5.5 background task: a tests:s13 workflow running for 3h32m, orchestrating 168 agents and consuming 2.8M tokens. Phases include Order and Baseline, with a 165/166 step grid spanning core, tests, hooks, integrate, gate, review, fix, and clean pipeline agents—showing real-world scale of parallel agent orchestration on Opus 5.5.
More from coding & agent
- Voice-controlled auto-advancing slides go viral; Tejas Kumar built the same in 2018 — TejasKumar_ · 2026-10-24
- Solo founder: after 6 months I stopped reviewing my AI agents' code — Al_Grigor · 2026-10-24
- Building an enterprise-wide custom agent platform: which UI/harness to use? — Electronic_Sort_6627 · 2026-10-24
- Dev wowed by Gemini 3.1 Sol: one prompt yields a glowing rainbow portal shader — Dimillian · 2026-10-24
- Hacker ran AI agents to breach 100+ sites at $50 each; researcher shares 5 Grok Bot defense prompts — alex_verem · 2026-10-24
- antirez now runs every side project with Claude and GPT cross-checking each other — antirez · 2026-10-24