SSO, RBAC & audit · Any model, your keys · No seat tax
The four-rung dunning ladder, minimum wait times between rungs, and the ledger format that carries each subscription's recovery state across hourly runs.
kortix marketplace install kortix-starter:dunning-escalation-skillmemory/payment-recovery-ledger.md. For every subscription
already tracked, note its current rung, the timestamp of its last action, and
its next-eligible-escalation time. Anything not yet on the ledger is a
candidate for Step 2.now >= next-eligible time; if
not, leave it alone this run.| Rung | Name | Action | Minimum wait before this rung |
|---|---|---|---|
| 1 | Smart retry | Retry the failed charge against the existing payment method via Stripe (off-session), no email sent yet | Immediately on first failure |
| 2 | Payment reminder | Friendly email: the charge didn't go through, here's the amount and a pay link | 24h after rung 1 if still failing |
| 3 | Update-your-card notice | Firmer email naming the likely cause (expired/declined card) with a direct link to update the payment method | 48h after rung 2 if still failing |
| 4 | Final notice | Clear, professional email stating this is the last automated reminder before the account needs manual attention | 72h after rung 3 if still failing |
awaiting-human on the ledger and
surface it in the Slack summary every run until a person acts or it pays.
Never cancel the subscription, issue a credit, or process a refund — that
decision, and the action, belongs to a human.recovered on the ledger with the rung it
was on when it cleared, stop sending it anything, and report it as a recovery
in the summary.awaiting-human, and
subscriptions that recovered since the last run. Omit subscriptions with no
change.memory/payment-recovery-ledger.md
(see <ledger-format>) before ending the turn.The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.
Daily runbook for budget pacing, CPA/ROAS drift, underperformer detection, and anomaly flags across Google Ads and Meta Ads, plus how to rank and word optimization recommendations.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Extract-and-match runbook for incoming vendor invoices: line-item extraction, PO/prior-invoice matching, duplicate + overcharge detection, and the ledger + approval hand-off.
Search, dedupe against the seen-mentions ledger, classify sentiment and notability, and post a digest with suggested response drafts — the daily brand-monitor runbook.