What problem does it solve? When AI coordinators spawn sub-agents for scoped work, handoffs often lack context, retry cycles multiply without bound, and outputs get accepted without verification. This Skill enforces a disciplined protocol that caps retries at 3 cycles, mandates WHY context in every spawn prompt, and requires coordinator validation before any issue is closed. ## Core Features & Use Cases - Structured Spawn Prompts: A mandatory four-section template (Task, WHY, Success criteria, Escalation path) ensures every sub-agent receives complete context. - 3-Cycle Protocol: Bounded retry logic with objective context forwarding between cycles and mandatory escalation after cycle 3 instead of endless loops. - Coordinator Validation & Dedup: A pre-acceptance checklist, mandatory GitHub issue deduplication search via gh issue list, and a research-then-execute rule requiring every analysis task to end with a concrete action (issue, PR, or decision record). - Use Case: A squad coordinator agent delegating a documentation update spawns a sub-agent with explicit acceptance criteria, validates the returned PR against the checklist, and escalates to .squad/decisions/inbox/ if three cycles fail to converge. ## Quick Start Use the iterative-retrieval protocol to spawn a sub-agent for my next scoped task, including WHY context, checkbox success criteria, and an escalation path.
