why

name

why

description

Honest second look at the recommendation the model just made — why it matters, the real reasoning behind it, and (the point) what it could be missing, quick and well-rounded. ONLY use when the user explicitly types the `$why` slash command. Do NOT trigger on the bare word "why" in ordinary conversation, nor on natural-language paraphrases like "why did you recommend that" — manual slash invocation only. Reviews the recommendation in the assistant's immediately-preceding turn (the message right before the user's). Dispatches one fresh Opus subagent, fed only that recommendation, to hunt blind spots with genuine distance, then synthesizes a concise review that surfaces real weaknesses instead of just defending the pick. Lightweight — a single scoped reviewer, not the multi-agent $impartial-review.

Codex Adapter

Read ../../../.claude/skills/why/SKILL.md completely and follow it as the canonical workflow for this skill.

• Resolve every relative script, reference, asset, and template path from the canonical skill directory under .claude/skills/why/.
• Read ../../../.agents/CODEX-SKILL-COMPATIBILITY.md and apply the status and exceptions for this skill.
• Translate Claude Code tool names to the available Codex equivalent as described by the repository AGENTS.md.
• Before any Claude Task, Agent, or Workflow step, confirm that the current Codex session exposes the required multi-agent tools. Do not replace independent review with self-review.
• Skill invocation alone does not authorize commit, push, PR, merge, deploy, migration, dependency installation, or another outward action unless that action is the user's explicit request.
• Follow Codex system, developer, sandbox, approval, and tool instructions when they differ from the canonical workflow.
• Keep the canonical Claude skill unchanged unless the user explicitly asks to edit the workflow itself.