Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add appeeky/stripe-skills --skill past-due-dunninggit clone --depth 1 https://github.com/appeeky/stripe-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/appeeky/stripe-skills/past-due-dunning)<a href="https://agentmods.dev/skills/appeeky/stripe-skills/past-due-dunning"><img src="https://agentmods.dev/badge/skills/appeeky/stripe-skills/past-due-dunning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/appeeky/stripe-skills/past-due-dunning"><img src="https://agentmods.dev/badge/skills/appeeky/stripe-skills/past-due-dunning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00485 |
| Opus 5.5 | $0.00026 | $0.00194 |
| Sonnet 5.5 | $0.00013 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
past-due-dunning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Past Due & Dunning
Stripe MCP Setup
Requires Stripe MCP connected via OAuth or restricted key. Docs: https://docs.stripe.com/mcp
GetMcpToolswithserver: "user-Stripe"(orplugin-stripe-stripe) before any call- Prefer
stripe_api_search→stripe_api_details→stripe_api_readfor list/retrieve - Always paginate —
limit: 100, followhas_morewithstarting_after - Amounts are in cents unless noted
- Never expose secret keys in output
Workflow
GetSubscriptionswithstatus: past_dueandstatus: unpaid— paginate all- Expand
default_payment_methodandlatest_invoice - Per sub record:
- Plan(s) + MRR
latest_invoice.attempt_count,amount_due,status- Card: brand, last4,
funding, country, wallet type
- Sum MRR at risk
Dunning Checklist (Dashboard)
- Smart Retries enabled (Billing → Revenue recovery)
- Customer emails: failed payment, card expiring
- Customer Portal: payment method update enabled
- Webhook:
invoice.payment_failedhandled in app
Output Template
Past Due Report ([date])
| # | Sub | Plan | MRR | Attempts | Card | Country |
|---|-----|------|-----|----------|------|---------|
Total: [N] subs | $[MRR]/mo at risk
Funding mix: credit [n] | debit [n] | prepaid [n]
Priority actions:
1. [highest $ sub with most attempts]
Route email gaps to email-dunning-setup; card patterns to card-funding-risk.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 53 lines · 65 tokens per session scan A 817432f3c17c
past-due-dunning is a skill published in the GitHub repository appeeky/stripe-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 485 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
past-due-dunning compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| past-due-dunningappeeky/stripe-skills | Skill | 5 | 3mo ago | MIT | A | 65 | Claude Code, Codex |
| stock-liquidityhimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 129 | Claude Code |
| company-valuationhimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 155 | Claude Code |
| fintel-datahimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 157 | Claude Code |
| earnings-recaphimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 112 | Claude Code |
| estimate-analysishimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 117 | Claude Code |
| alpha-vantageforyourhealth111-pixel/Vibe-Skills | Skill | 3.8k | 3d ago | Apache-2.0 | A | 126 | Claude Code, Codex |