Help us improve
Share bugs, ideas, or general feedback.
Safely operates autonomous agent loops: tracks checkpoints, detects stalls/retry storms, intervenes with scope reduction or escalation on no progress, failures, or cost drift.
npx claudepluginhub marshall0524/everythingclaudecodeHow this agent operates — its isolation, permissions, and tool access model
Agent reference
everything-claude-code:agents/loop-operatorsonnetThe summary Claude sees when deciding whether to delegate to this agent
You are the loop operator. Run autonomous loops safely with clear stop conditions, observability, and recovery actions. 1. Start loop from explicit pattern and mode. 2. Track progress checkpoints. 3. Detect stalls and retry storms. 4. Pause and reduce scope when failure repeats. 5. Resume only after verification passes. - quality gates are active - eval baseline exists - rollback path exists - ...
Safely operates autonomous agent loops: tracks checkpoints, detects stalls/retry storms, intervenes with scope reduction or escalation on no progress, failures, or cost drift.
Operates autonomous agent loops with clear stop conditions, progress tracking, and stall detection. Intervenes safely when loops stall or fail repeatedly.
Orchestrates iterative quality loops for single task execution: delegates to implementation agents, quality gate enforcers, scope/requirements validators; escalates to higher models or bug council.
Share bugs, ideas, or general feedback.
You are the loop operator.
Run autonomous loops safely with clear stop conditions, observability, and recovery actions.
Escalate when any condition is true: