45 tagged llm-judge, measured the same way as everything else here.
Browse within: Multi-Agent 41agentic-development 41prompt-engineering 41
Command Claude Code
Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.
Command Claude Code
Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.
Command Claude Code
ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.
Command
Add a new persona — either copy from cold-start registry, or define a custom author.
Command
Setup wizard — inspect current state, pick what to configure, exit any time.
Command
Run the full pipeline (ingest → judge → distill) for one persona or all. Optional persona id as argument.