Use when a user's request is vague, ambiguous, or underspecified. Explores the codebase first, then runs an iterative Q&A loop grounded in the findings until ambiguity is gone. Outputs a clear, well-scoped context brief so the user can plan sharply. Triggersโฆ
Corrective cleanup of AI-generated code โ removes LLM-specific patterns while preserving behavior. Use when the user says "deslop", "slop", "clean AI code", "remove AI patterns", or when you spot LLM-generated code smells after any generation session. Forโฆ
Orchestrates multi-day execution of complex tasks through milestones. Each milestone goes through plan-crafting, run-plan (worker-validator), and review-work phases with checkpoint/recovery. Runs autonomously end-to-end โ no per-milestone approval gates;โฆ
Decomposes complex, multi-day tasks into optimized milestones (ultraplan). Broad parallel exploration grounds a draft milestone DAG, then independent adversarial critics attack the draft in rounds until no blocking findings remain. Triggers when the user saysโฆ
Use when a task's scope is clear and multi-step implementation is needed, before touching code. Triggered after clarification is complete, or when the user explicitly requests plan creation with a clear prompt.
Use after run-plan completes to independently verify the implementation. Reads only the plan document and inspects the codebase from scratch โ information-isolated from the execution context. Produces a structured review document with PASS/FAIL verdict.โฆ
Use when you have a written implementation plan to execute. Loads the plan, reviews critically, executes tasks in dependency order, and reports completion. Triggers when the user says "run the plan", "execute the plan", or "let's start implementing".
Use when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-first, failing-test-first debugging workflow before fixing.