Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
How this command is triggered — by the user, by Claude, or both
Slash command
/autopoiesis:brainhookThe summary Claude sees in its command listing — used to decide when to auto-load this command
Toggle the BrainHook "infinite loop mode" enforcement. When ON, every time you try to stop, you'll be reminded to: - Look again even if you think you're done - Check for missed aspects - Decide whether to fix issues found - Act on those decisions This enforces the "LLMs lack global coherence" principle - keep iterating until the user breaks you out. Current state file: /tmp/brainhook_state.txt Instructions: 1. Check current state by reading /tmp/brainhook_state.txt (if missing = off) 2. Toggle it: if "on" write "off", if "off" or missing write "on" 3. Report the new state to user Do th...
Toggle the BrainHook "infinite loop mode" enforcement.
When ON, every time you try to stop, you'll be reminded to:
This enforces the "LLMs lack global coherence" principle - keep iterating until the user breaks you out.
Current state file: /tmp/brainhook_state.txt
Instructions:
Do this now.
npx claudepluginhub sancovp/autopoiesis-mcp --plugin autopoiesis/fire-loopRuns a self-iterating autonomous loop that persists until a task completes, with circuit breaker health checks, error classification, context engineering, and approach rotation.
/loopPursues a standing goal by repeatedly working through a prioritized backlog, learning each cycle. Self-healing and durable across sessions via re-arm hooks.
/helpExplains the Loop iterative AI methodology and lists available loophaus commands: /loop, /loop-stop, /loop-plan, /loop-pulse, /loop-orchestrator.
/helpExplains the Ralph Wiggum technique for iterative AI development via continuous Claude loops and lists all available Ralph Wiggum plugin commands with usage examples.
/helpExplains the Ralph Loop iterative development technique (self-referential AI loops) and lists available commands /ralph-loop and /cancel-ralph with usage examples.
/helpExplains the Ralph Wiggum technique (iterative AI loop methodology) and lists available commands: /wiggum-loop and /cancel-wiggum.