This prevents a sneaky context overflow issue where TaskOutput dumps entire agent transcripts (70k+ tokens) into your main conversation, triggering mid-conversation compaction and defeating the whole point of isolated agent contexts. It enforces using Task in synchronous mode instead, which keeps the agent work contained and just returns a summary. Born from an actual session where someone got bitten by this. If you're running background tasks and wondering why your context suddenly exploded, this is your guardrail. Simple rule, solves a real footgun.
npx -y skills add parcadei/continuous-claude-v3 --skill no-task-output --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills