Split an approved plan into parallel tmux panes in the current window so the user can watch agents work. Prefer this visual flow by default; use `omp team` only when the user explicitly wants background execution or runtime messaging/status APIs.
Gate-driven retry loop — re-run an agent until a shell gate command passes (e.g. PR checks green, tests passing). Use with /loop when a machine-checked condition decides done-ness, not the model's say-so.
Use when the user invokes /goal, wants a durable objective for the current Copilot session, asks to resume an unfinished objective, or needs turn-based continuation with completion and blocker decisions.
Use when the user invokes /project-goal, wants to set or inspect the repository's durable north-star, or asks what the project is trying to achieve across sessions.
Single-owner execute-fix-verify loop for one clear task. Use with /ralph when one agent should keep going until evidence or blocker.
Stateful multi-session teaching loop. Builds knowledge, skills, and wisdom from trusted sources via short interactive lessons grounded in a mission. Use with /teach when the user wants to learn a topic over time.
Use when the user invokes /ultragoal, wants a durable multi-story objective, provides a Ralplan artifact for sequential execution, or requires criterion evidence and independent completion gates.
Adversarial QA pass that tests behavior, failures, and regressions. Use with /ultraqa after implementation when shallow checks are not enough.