What problem does it solve? Running autonomous AI agent loops in production often leads to uncontrolled churn, repeated retries on the same root cause, stalled merge queues, and unbounded cost escalation. This Skill provides a canonical loop pattern with quality gates, evaluation, and recovery controls so long-running agent workflows stay measurable and recoverable. ## Core Features & Use Cases - Loop Selection Flow: Routes work to the right loop mode based on need: continuous-pr for strict CI/PR control, rfc-dag for RFC decomposition, infinite for exploratory parallel generation, or sequential as the default. - Combined Production Pattern: Recommends a stack combining RFC decomposition, code quality gates, an eval harness loop, and session persistence. - Failure Mode Recovery: Defines concrete recovery steps such as freezing the loop, running a harness audit, reducing scope to the failing unit, and replaying with explicit acceptance criteria. - Use Case: A team running an overnight autonomous coding agent notices cost drift and repeated failed retries; they apply this Skill to freeze the loop, audit the harness, and restart with scoped acceptance criteria. ## Quick Start Ask the agent to set up a continuous agent loop with quality gates and an eval harness for your current coding task, selecting the appropriate loop mode for your workflow.
