79yuuki/dotfiles/standup

Superset Standup

Answer "what happened while I was away?" from real state, not guesses. Entirely read-only.

1. Sweep

Run bash scripts/sweep.sh from this skill's directory (bash ${CLAUDE_SKILL_DIR}/scripts/sweep.sh in Claude Code). It lists workspaces and tasks, then for each workspace lists its terminals and reads the last screen of every agent terminal, tolerating individual failures. Pass --host <id> to sweep a remote host, --max-lines <n> to change the per-terminal tail (default 60).

If the script can't run (no bash, no jq), do the same by hand: superset workspaces list --json, superset tasks list --json, then per workspace superset terminals list --workspace <id> --json and superset terminals read --workspace <id> --terminal <terminalId> --max-lines 60.

The last screen of a terminal shows whether the agent finished, asked a question, or errored.

2. Classify each workspace

• Needs you: agent finished and awaits review, asked a question, or hit a permission prompt or failure
• In flight: actively working
• Blocked: waiting on something external
• Stale: idle with no pending work, a candidate for cleanup

3. Report

Lead with what needs the user, one line per item: workspace, agent, state, and the next action. Then in-flight, then completed, then stale-workspace cleanup suggestions. Keep the whole digest scannable: no terminal dumps, quote at most the single relevant line an agent printed.

Rules

Never send input to a terminal, modify tasks, or clean anything up as part of the digest. Offer those as follow-ups and act only when asked.