Pick the next work in an epic or bead graph; closed is not proven. Use when: asked what is next or whether an epic is done.
Measure whether a skill helps by comparing runs with and without it. Use when: reading skill A/B results or deciding to keep, revise or remove one.
Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in parallel, even two; check scopes before any launch.
Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.
Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p` call, even a simple one.
Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.
Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.
Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a /goal prompt); one change goes to Plan.