Stats
Actions
Tags
Starts a managed autonomous loop pattern with configurable mode and safety defaults. Creates a loop plan and runbook with explicit stop conditions.
How this command is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:loop-startThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Loop Start Command Start a managed autonomous loop pattern with safety defaults. ## Usage `/loop-start [pattern] [--mode safe|fast]` - `pattern`: `sequential`, `continuous-pr`, `rfc-dag`, `infinite` - `--mode`: - `safe` (default): strict quality gates and checkpoints - `fast`: reduced gates for speed ## Flow 1. Confirm repository state and branch strategy. 2. Select loop pattern and model tier strategy. 3. Enable required hooks/profile for the chosen mode. 4. Create loop plan and write runbook under `.claude/plans/`. 5. Print commands to start and monitor the loop. ## Required ...
Start a managed autonomous loop pattern with safety defaults.
/loop-start [pattern] [--mode safe|fast]
pattern: sequential, continuous-pr, rfc-dag, infinite--mode:
safe (default): strict quality gates and checkpointsfast: reduced gates for speed.claude/plans/.ECC_HOOK_PROFILE is not disabled globally.$ARGUMENTS:
<pattern> optional (sequential|continuous-pr|rfc-dag|infinite)--mode safe|fast optionalnpx claudepluginhub ysyecust/everything-claude-code --plugin everything-claude-code/loop-startStarts a managed autonomous loop pattern with configurable mode and safety defaults. Creates a loop plan and runbook with explicit stop conditions.
/loop-startStarts a managed autonomous loop with configurable patterns and safety defaults. Supports sequential, continuous-pr, rfc-dag, and infinite modes with safe or fast execution profiles.
/loopRuns autonomous multi-agent (Claude/Codex) loops to execute coding tasks iteratively until completion, using isolated git worktrees, parallel mode, and configurable polishing passes.
/fire-loopStarts a self-iterating autonomous loop with circuit breaker, error classification, and context-aware execution until a task is completed or a safety limit is reached.
/helpExplains Loophaus plugin: iterative AI development via Ralph Wiggum continuous Claude loops, lists commands (/loop, /loop-plan, /loop-stop, etc.), skills, and key concepts.
/loopParses natural language task into components (task, max iterations, completion condition) and sets up repeating AI execution loop via bash script.