Paseo — итеративный цикл агента до условия выхода

★ 7.7 · orchestration

paseo-loop is a Claude Code skill that runs an iterative worker/verifier agent loop until a specified exit condition is met. It is part of the Paseo ecosystem, which orchestrates agents across Claude Code, Codex, Copilot, OpenCode, and Pi through a unified interface. The skill is triggered by commands such as loop, babysit, keep trying until, or watch, enabling fully autonomous iterative execution with per-iteration verification. It is designed for workflows that require continuous monitoring, polling for a target state, or retrying an action until it succeeds — all without manual intervention between attempts.