feat(security-review): schedule the Plane-1 checker coordinator nightly + role-skip

- checker_coordinator.sh: add COORDINATOR_SKIP_ROLES env (comma-separated) to drop
  roles whose credentials are not provisioned from the registry entirely (never
  canaried/run/ALARMed). Fail-safe: empty/unset = run all.
- systemd: sea-haven-checkers.{service,timer} run the coordinator nightly at ~03:30
  UTC (90 min after the secrev sweep so they don't contend on $MIRROR_DIR / the
  Claude pool). The unit sets COORDINATOR_SKIP_ROLES=aws-posture,confluence-doc
  (aws-posture needs IAM Roles Anywhere; confluence-doc needs the confluence-bot
  token — both intentionally unprovisioned).

Deployed + enabled on the box (deploy-before-merge): canary 4/4 with the skip,
timer scheduled for 2026-06-23 03:35 UTC.
This commit is contained in:
Adam Moussa 2026-06-22 19:03:22 -04:00
parent e875d97cbf
commit 912828b6b7
3 changed files with 83 additions and 0 deletions

View file

@ -145,6 +145,23 @@ if [ "$SQUEEZE" -eq 1 ]; then
)
fi
# Operator role-skip (COORDINATOR_SKIP_ROLES="aws-posture,confluence-doc"): remove
# roles whose backing credentials are not provisioned (aws-posture needs IAM Roles
# Anywhere; confluence-doc needs the confluence-bot token). A skipped role is
# dropped from the registry entirely — never canaried, run, or ALARMed — so the
# nightly schedule only exercises credential-ready checkers. Empty/unset = run all.
if [ -n "${COORDINATOR_SKIP_ROLES:-}" ]; then
declare -a _kept=()
for entry in "${ROLES[@]}"; do
_name="$(role_field "$entry" 1)"
case ",${COORDINATOR_SKIP_ROLES}," in
*",${_name},"*) log "SKIP role '$_name' (COORDINATOR_SKIP_ROLES)" ;;
*) _kept+=( "$entry" ) ;;
esac
done
ROLES=( ${_kept[@]+"${_kept[@]}"} )
fi
# ==============================================================================
# DURABLE STATE (design §6.7): atomic write-temp-then-rename + integrity check.
# Integrity = schema_version match + stored content_hash + logical-consistency.

View file

@ -0,0 +1,46 @@
# sea-haven-checkers.service — Plane-1 nightly checker coordinator (sh-secrev VM, user adam).
#
# Runs security-review/checker_coordinator.sh: the read-only Plane-1 checkers
# (compliance-drift, dependency-cve, doc-drift, plan-groomer) under ONE shared
# budget ledger + versioned rotation/coverage, ALARM-only to Slack. Reuses the
# secrev sweep's substrate ($MIRROR_DIR clones, budget discipline) — no re-clone.
#
# Install (on the VM, as root):
# sudo cp sea-haven-checkers.service /etc/systemd/system/
# sudo cp sea-haven-checkers.timer /etc/systemd/system/
# sudo systemctl daemon-reload
# sudo systemctl enable --now sea-haven-checkers.timer # the timer drives it
# systemctl list-timers sea-haven-checkers.timer
#
# Secrets/config come from the EnvironmentFiles (leading '-' = optional):
# ~/secrev.env -> CLAUDE_CODE_OAUTH_TOKEN, GH_TOKEN, SLACK_WEBHOOK_URL
# ~/orchestrator/.env -> OPENAI/etc. (only if a checker shells the cross-model run.py)
#
# COORDINATOR_SKIP_ROLES excludes roles whose creds are NOT provisioned:
# - aws-posture needs IAM Roles Anywhere / step-ca (not provisioned)
# - confluence-doc needs the confluence-bot Atlassian token (not provisioned)
# Remove a name here once its credential is provisioned to bring that checker online.
[Unit]
Description=Sea Haven agent-team Plane-1 nightly checker coordinator
After=network-online.target
Wants=network-online.target
[Service]
Type=oneshot
User=adam
WorkingDirectory=/home/adam/orchestrator/security-review
EnvironmentFile=-/home/adam/secrev.env
EnvironmentFile=-/home/adam/orchestrator/.env
Environment=GH_ORG=Sea-Haven-Industries
Environment=COORDINATOR_SKIP_ROLES=aws-posture,confluence-doc
# Tune the shared ceiling without editing the script (uncomment to override):
# Environment=TOTAL_BUDGET_USD=120
# Environment=MAX_CYCLE_NIGHTS=4
ExecStart=/home/adam/orchestrator/security-review/checker_coordinator.sh
# Bounded so a hung checker cannot run forever; spend is capped by TOTAL_BUDGET_USD.
TimeoutStartSec=10800
Nice=10
[Install]
WantedBy=multi-user.target

View file

@ -0,0 +1,20 @@
# sea-haven-checkers.timer — fires the Plane-1 checker coordinator nightly.
#
# 03:30 UTC — ~90 min after the sea-haven-secrev sweep (02:00) so the two do not
# contend on $MIRROR_DIR or the shared Claude subscription pool at the same instant.
# Persistent=true → if the VM was off, it runs at next boot. RandomizedDelaySec
# spreads load off an exact-minute spike.
#
# Install: see the header of sea-haven-checkers.service.
[Unit]
Description=Run the Sea Haven Plane-1 checker coordinator nightly (~03:30 UTC)
[Timer]
OnCalendar=*-*-* 03:30:00
Persistent=true
RandomizedDelaySec=600
Unit=sea-haven-checkers.service
[Install]
WantedBy=timers.target