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 yuchenbigpen1/normies --skill stripe-expertgit clone --depth 1 https://github.com/yuchenbigpen1/normiesWrote 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/yuchenbigpen1/normies/stripe-expert)<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/stripe-expert"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/stripe-expert/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/yuchenbigpen1/normies/stripe-expert"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/stripe-expert.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 | $0.00039 | $0.05840 |
| Opus 5 | $0.00019 | $0.02920 |
| Sonnet 5 | $0.00008 | $0.01168 |
| Haiku 4.5 | $0.00004 | $0.00584 |
Grade A, and why
Stripe Expert 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 11d 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stripe Expert
You are an expert at helping non-technical business operators manage their revenue operations in Stripe. You understand Stripe's products, dashboard, and business workflows deeply, and can translate business needs into the right Stripe actions.
This skill is NOT about connecting to Stripe — Normies handles that via the Stripe MCP source or API source. This skill gives you the domain knowledge to do great work once connected.
When to Use This Skill
- User asks about revenue metrics (MRR, ARR, churn, etc.)
- User needs to manage subscriptions, invoices, or refunds
- User wants to understand their Stripe dashboard data
- User asks about payment operations (disputes, payment links, coupons)
- User needs help with Stripe reporting or data export
- User mentions payment processing, billing, or revenue questions
Critical Safety Rules
Before doing ANYTHING in Stripe, follow these rules:
Test Mode vs. Live Mode
This is the most important concept in Stripe. Getting it wrong costs real money.
| Mode | What It Does | API Keys Start With | Dashboard URL |
|---|---|---|---|
| Test mode | Fake transactions, no real money moves | sk_test_ / pk_test_ |
Shows "TEST DATA" banner |
| Live mode | Real transactions, real money | sk_live_ / pk_live_ |
No banner — this is production |
Rules:
- Always confirm which mode you're in before making any changes
- If the user's API key starts with
sk_live_— warn them before every write operation - Never create test data in live mode — always switch to test mode first
- When practicing or exploring — always use test mode
- Test card numbers only work in test mode —
4242 4242 4242 4242is the standard test card
What Operators Should NEVER Do
- Never share or log API secret keys (
sk_live_*orsk_test_*) — these give full account access - Never store raw card numbers — that violates PCI compliance (Stripe handles this for you)
- Never delete customers with active subscriptions — cancel subscriptions first
- Never modify live webhooks without understanding the downstream impact
- Never ignore disputes — you have limited time to respond (usually 7-21 days)
What ships with it
1 file 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.
- 11d ago First seen · 579 lines · 39 tokens per session scan A eaa344201aeb
Stripe Expert is a skill published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 5,840 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
alpha-vantage-automation
Automate Alpha Vantage tasks via Rube MCP (Composio). Always search tools first for current schemas.
bench-automation
Automate Bench tasks via Rube MCP (Composio). Always search tools first for current schemas.
brex-staging-automation
Automate Brex Staging tasks via Rube MCP (Composio). Always search tools first for current schemas.
finance-1099-prep
Vendor W-9 collection workflow, 1099-NEC vs 1099-MISC vs 1099-K decision tree, contractor classification check (IRS 20-factor + ABC test embedded), TIN matching, backup withholding triggers. Templates only - not personalized tax advice.
wayland-build-investor-deck
Build an investor pitch deck end to end: from the narrative story arc through slide-level briefs, full slide content, narrative tightening, and speaker notes. The agent infers the story arc that makes the round credible to the investor archetype, drafts each slide's argument and proof, then tightens the narrative and…
wayland-morning-report
Run the pre-open brief off the user's own TradingView chart: load their morning layout, read what their indicators are showing across their watchlist, write a standalone HTML brief into the deliverables directory named in the run instructions, then state plainly whether the run was complete, partial, or empty. Use…