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 JasonColapietro/suede-creator-skills --skill subscription-recoverygit clone --depth 1 https://github.com/JasonColapietro/suede-creator-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/jasoncolapietro/suede-creator-skills/subscription-recovery)<a href="https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/subscription-recovery"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/subscription-recovery/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/jasoncolapietro/suede-creator-skills/subscription-recovery"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/subscription-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 125 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00150 | $0.01886 |
| Opus 5 | $0.00075 | $0.00943 |
| Sonnet 5 | $0.00030 | $0.00377 |
| Haiku 4.5 | $0.00015 | $0.00189 |
Grade A, and why
subscription-recovery 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subscription Recovery
IRON LAW: Never cancel, dispute, or contact a merchant about a service until the
user has named that specific service and the specific outcome they want for it.
A subscription appearing in a discovery list is not authorization to act on it.
Prerequisites
- Claude in Chrome browser extension connected, for any service checked or acted on
in-browser. If
mcp__claude-in-chrome__*tools aren't loaded yet, fetch them via ToolSearch first. - Unlike amazon-returns-recovery, there is no single account to sweep — discovery depends on what the user can provide (a bank/card statement, app access, or just naming what they remember paying for) and what platform-level subscription hubs are available (App Store, Google Play, PayPal).
- Unvalidated click-paths. Only the App Store, Google Play, and PayPal hub pages in Phase 1a are close to a fixed, checkable URL. Every individual service's own billing/cancellation page (Netflix, Spotify, a gym's member portal, etc.) has to be discovered live and should be recorded in references/service-playbook.md once confirmed, so the next run doesn't rediscover it from scratch.
Phase 1a — Platform subscription hubs (read-only, no side effects)
These three cover a large share of subscriptions in one page each, because the platform (not the individual service) is the merchant of record:
- Apple App Store (iOS/iPadOS/Mac subscriptions bought through Apple's
in-app-purchase flow — many streaming apps route here instead of billing
directly):
https://apps.apple.com/account/subscriptions(requires Apple ID sign-in) or on-device: Settings → [Apple ID] → Subscriptions. - Google Play:
https://play.google.com/store/account/subscriptions— same idea for Android-purchased subscriptions. - PayPal recurring payments:
https://www.paypal.com/myaccount/autopay/— lists every merchant with standing authorization to charge the account, including ones that don't show up anywhere else (a common blind spot: an old free trial that converted, billed via PayPal, with no reminder email ever opened).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 149 lines · 150 tokens per session scan A 8a1ec52570a6
subscription-recovery is a skill published in the GitHub repository JasonColapietro/suede-creator-skills (135 stars, last pushed today), licensed MIT. It adds 150 tokens to every session and 1,886 once invoked, about $0.0007 per session on Opus 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 2026-08-30.
Other skills, from other repositories
agb-bei-kreditvertraegen-verbraucherdarlehen
Für AGB bei Kreditverträgen Verbraucherdarlehen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
agb-in-kapitalanlagen-effektenhandel
Für AGB in Kapitalanlagen Effektenhandel: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
mahngebuehren-und-zinsanpassung-agb
Für Mahngebühren und Zinsanpassung AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Berechnungstabelle mit Annahmen und Kontrollfragen.
cost-optimization
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost…
stripe-payments
Add Stripe payments to a web app — Checkout Sessions, Payment Intents, subscriptions, webhooks, customer portal, and pricing pages. Covers the decision of which Stripe API to use, produces working integration code, and handles webhook verification. No MCP server needed — uses Stripe npm package directly. Triggers…
financial-document-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.