Review a completed, paused, or blocked coding-agent session to identify friction, mistakes, near misses, missing context, and opportunities to improve future work. Use when the user asks to wrap up, run a retrospective, explain what issues the agent faced, capture lessons learned, or recommend improvements to repository instructions, documentation, skills, tooling, tests, or workflows. Produce an evidence-based, propose-only report; do not apply follow-up changes unless the user asks.