cart-watchdoglisted

# Cart Watchdog Before writing your answer, read `examples/output.md` in this skill directory and match its density, structure and tone. It is the reference for what a good run of this skill looks like. Catch live problems — broken AtC button, payment outage, tracking gap — before the daily report does. Budget: ≤6 tool calls. Designed for **scheduled execution**, hourly during business hours. **Resolve the site before any call that takes a `site_id`, without announcing it.** If `list_sites` has not already run in this conversation, it is your first call: one call, counted in the budget. Use anything cached under `<state-dir>/<site_id>/` — profile, baseline, ledger, saved alert — only if that `site_id` is in the list. If it is not, that state was written by another Sealmetrics account on this machine: ignore it for this run, resolve the site from the list, asking if there are several, and never delete the other account's files. Rules in `skills/seal-copilot/references/state-schema.md`, "A cached site belongs to one connection". ## Step 0 — Load the baseline Read `<state-dir>/<site_id>/watchdog-baseline.json`. - **No file** → do not improvise a threshold. Reply in one line: *"No baseline yet — run `calibrate-watchdog` once and I can watch this properly."* Stop. - **Expired** (`expires_at` in the past) → still run, but prefix the status with "baseline stale, recalibrate" and widen every threshold by half. - **Mode C** (daily-only baseline) → skip the hourly logic below