diff --git a/.claude/skills/openstack-cloud-ops/SKILL.md b/.claude/skills/openstack-cloud-ops/SKILL.md index c7c78ec..c9cef78 100644 --- a/.claude/skills/openstack-cloud-ops/SKILL.md +++ b/.claude/skills/openstack-cloud-ops/SKILL.md @@ -35,6 +35,11 @@ The repo is a living draft; this skill's invariants (discipline, hardening) change slowly, its facts (IPs, versions, phase status) go stale fast. +**Long sessions get compacted.** At session start (and after any compaction), read +`docs/session-ledger.md` and run `bash scripts/ledger-scan.sh` to recover what is in flight and +reconcile it against repo ground truth (open decisions, open security rows, next-free numbers). +Update the ledger at every deliverable -- it is standing, like the changelog. See +`references/operating-discipline.md` (Session continuity). ## Step 1 - detect the environment - **Live shell to the jumphost / infra** (Claude Code on `vopenstack-jesse` or @@ -81,6 +86,7 @@ | Full-cloud restart after outage/maintenance | repo `runbooks/ops-restart-procedure.md` | | Starting any consequential live session | `bash scripts/run-logged.sh