FLEET.md's wake conditions gain #50 D16: notify.sh's second query (open
issues and PRs labelled needs-ruling), one tracked message per item edited
in place across the ladder's four rungs and removed on clearance, the
message's contents, triage's past-24h pickup, and the on-paper caveat.
Nothing box-side sets, clears or decides the flag.
Part of #50. Closes#74.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A descriptive snapshot of how the five-box fleet actually runs: the roster
table, the duty-loop skeleton (cron + flock + poll + one-shot sessions),
wake conditions per role, the resilience layer (boot gate, crash-only
resume, checkpoint discipline, worktree isolation), and board conventions.
Explicitly not doctrine and not vendored: it exists so the current setups
can later be captured in detail per-agent and converged into a reusable
fleet-management solution.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
