test-cards

A reference for Stripe's test card numbers and the payment outcomes they simulate, such as successful payments, declines, and extra authentication.

In plain words
What is it for?
Use it to choose test cards for specific scenarios and build matching payment tests. These cards work only in Stripe test mode.
Why use it?
It lets you test payment flows without using real cards or real transactions.

Command

Install

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.

agentmods
npx agentmods add commands/stripe/ai/test-cards
Clone the repo
git clone --depth 1 https://github.com/stripe/ai
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00009 $0.00233
Opus 5 $0.00005 $0.00117
Sonnet 5 $0.00002 $0.00047
Haiku 4.5 $0.00001 $0.00023

Measured 2d ago against content hash 4e2496258654, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-cards 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

providers/claude/plugin/commands/test-cards.md · 25 lines

What it actually says

Test Cards Reference

Provide a quick reference for Stripe test card numbers:

  1. If a scenario argument is provided (e.g., "declined", "3dsecure", "fraud"), show relevant test cards for that scenario
  2. Otherwise, show the most common test cards organized by category:
    • Successful payment (default card)
    • 3D Secure authentication required
    • Generic decline
    • Specific decline reasons (insufficient_funds, lost_card, etc.)
  3. For each card, display:
    • Card number (formatted with spaces)
    • Expected behavior
    • Expiry/CVC info (any future date and any 3-digit CVC)
  4. Use clear visual indicators (✓ for success, ⚠️ for auth required, ✗ for decline)
  5. Mention that these only work in test mode
  6. Provide link to full testing documentation: https://docs.stripe.com/testing.md

If the user is currently working on test code, offer to generate test cases using these cards.

Changes

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.

  1. 2d ago First seen · 25 lines · 9 tokens per session scan A 4e2496258654

Subscribe to this mod's changes

test-cards is a command published in the GitHub repository stripe/ai (1,785 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 233 once invoked, about $0.0000 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.