Give AI agents accurate knowledge on Autopilot

/loop 30m Start the "Give AI agents accurate knowledge on Autopilot" loop.

Inspired by Captain (https://runcaptain.com).

Goal: open work triaged, exceptions owned, and core integrations workflow current with audit trail
Max iterations: 20
Between iterations run: Report open queue items, stale tasks, failed automations, and items awaiting human approval for Captain
Exit when: zero open items without owner or explicit escalation, all external actions approved or sent, and systems of record current

Step 1 — Monitor queue: Scan inbound work, alerts, and backlog items for Captain.
Step 2 — Triage and prioritize: Rank by SLA, revenue impact, and compliance risk.
Step 3 — Execute workflow: Run the core automation with human checkpoints where required.
Step 4 — Review exceptions: Escalate ambiguous cases; require sign-off on external actions.
Step 5 — Close and report: Update systems of record and report open gaps for next pass.

## Before you start

Connect plugins:
- GitHub (required) — Read branches, PRs, reviews, checks, workflow runs, and source diffs.

Attach skills:
- Loop runner (required) — Self-pace iterations, run the check between passes, and stop only on the exit condition.
- Code change + local verification (optional) — Edit code safely, run commands, and keep changes scoped.
- CI debugging (optional) — Read failing checks, logs, and the smallest actionable root cause.
- Approval workflows (optional) — Keep outbound actions in draft or approval states when risk is non-trivial.

Self-pace this loop. After each iteration, run the check command, read the output, and only continue if the exit condition is not met. Stop when the exit condition passes or max iterations is reached. Give a short status update each pass.