Stops Claude from burning tokens by obsessively polling background agents in sleep loops. When you launch parallel agents with run_in_background, Claude's instinct is often to check status files every few seconds until they complete. This skill teaches it to launch the agents and then just continue working or chatting until you actually need the results. Check status only when the user asks or when you hit a blocking dependency. Comes from user feedback that agents can just ping when they're done, so there's no reason to sit there polling like it's 2005.
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill no-polling-agents