Why

---
name: why
description: "Fresh critical second look at a recommendation: on $why, or before presenting own weighty pick (hard to undo, 2+ real options, real time or money at stake). Never from ordinary why questions."
---

# Second look at a recommendation

Scope to the recommendation the user names, otherwise the immediately preceding recommendation. If none exists, say so. Ask only if several materially different choices cannot be disambiguated.

Self-run mode: when you invoke this yourself before presenting a weighty pick, review the recommendation you are about to give, with the user message that prompted it as context. Then present the refined recommendation in the session's normal style with one added line, `Pressure-tested ($why): <what the reviewer changed or confirmed>`, leading with the new pick if the check overturned it. Make no file edits for the pick until the user answers.

Session-brief mode: when a task brief opens with a `$why` (or `/why`) step on its recommendation, run it first regardless of weight. Review the brief's recommendation against freshly fetched `origin/main`, giving the reviewer only the brief. If the check rejects it, report why and do not start the brief's work until the user answers. If it refines it, apply the refinement, proceed, and state the change in your first report. If it confirms it, proceed. Report with one line, `Pressure-tested ($why): <what the reviewer changed or confirmed>`. This is the one case where the brief's own work follows the check without waiting for the user.

Verify the few facts the recommendation depends on. With an exposed collaboration tool, give one fresh read-only leaf reviewer the recommendation and minimal necessary context using fork_turns: "none". Honor an explicit user model choice; otherwise inherit the configured model. Check actual exposure and disclose an unavailable requested model rather than silently substituting it. Ask for missed assumptions, costs and circumstances that would change the decision. No nested review or mutation.

If the independent reviewer is unavailable or fails, explicitly report the missing independent check. You may provide clearly labeled personal reasoning, but cannot claim the independent workflow completed. Do not silently replace it with self-review.

Check the candidate criticisms locally, then explain the reasoning, real weaknesses and whether you still recommend the choice. Keep it short and readable; a clean finding is valid. This is analysis, not authorization to implement a different approach.