Retro

Review a session transcript. Report how well it ran, where the time went, and what to change next time.

Rules

Default to the current session. Find it by this session's ID, never by the newest file; parallel sessions share a project folder. Accept a session ID or a transcript path instead. Include subagent transcripts, since their work counts too. OpenCode keeps sessions in a database, so say it is not supported.
Condense the transcript before you read it. Transcripts run to megabytes, mostly tool output. Extract a short timeline: each user prompt, and each tool call with its time, duration, input, and error. Read a full result only when one error needs it.
Time each phase. Phases are understanding, implementing, testing, reviewing, and other (git, CI, deploy). A phase lasts until the next one starts. Time waiting for the user is not agent time; report it apart. Questions to the user and permission prompts count as user wait. Background tasks finish later than their call shows, so use their completion notice. Skip this retro's own calls.
Flag slow checks run again for no reason. Slow means Playwright, e2e, integration, full suites, or CI watches. A rerun is waste when no covered code changed, or a narrower check would have proved the fix. A rerun after a relevant change is fine.
Group tool-call errors by cause. Examples: bad path, bad args, permission denied, missing command. A failing call retried unchanged matters most.