forge-payments

forge-payments is a skill for Claude Code from ForgeyClap/claude-forge. It costs 50 tokens per session (1,438 once invoked), scanned A, original, MIT.

A playbook for connecting software to payment providers such as Stripe, Mollie, Adyen, and PayPal. It covers checkout, subscriptions, refunds, webhooks, and related payment-safety rules.

In plain words
What is it for?
Use it to design or review payment flows, recurring billing, refunds, webhook verification, currency and amount handling, and 3D Secure steps.
Why use it?
It helps avoid exposing card details, processing the same payment twice, mishandling money amounts, or treating an unverified sandbox integration as production-ready.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Codex.

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 skills/forgeyclap/claude-forge/forge-payments
Any agent
npx skills add ForgeyClap/claude-forge --skill forge-payments
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code.

Wrote 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.

agentmods badge for forge-payments

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-payments.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-payments)
Your own site
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-payments"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-payments.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,438 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 5.1 $0.00050 $0.01438
Opus 5 $0.00025 $0.00719
Sonnet 5 $0.00010 $0.00288
Haiku 4.5 $0.00005 $0.00144

Measured 5d ago against content hash b00b86b26334, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

forge-payments 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 5d 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.

.claude/skills/forge-payments/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge playbook — Payments / checkout / billing

This is a money + secrets + PCI-scope domain. The payment-integration specialist (.claude/agents/payment-integration.md) leads the payment-specific work under Integration Boss or Build Boss. security-reviewer / codex-reviewer are useful (optional) advisors — payments is exactly the "high-risk" case where Codex-on-request earns its keep. Never claim PCI compliance or a working live charge that wasn't verified in the sandbox.

Hard rules (non-negotiable)

  • No raw PAN, ever. Card data is captured by the gateway's tokenization / hosted fields / hosted checkout (Stripe Elements or Checkout, Mollie/Adyen hosted, PayPal SDK) — the raw card number, CVV, and full track data never touch your server, logs, DB, memory files, or the repo. This keeps you in PCI DSS v4.0.1 SAQ A / SAQ A-EP scope instead of full SAQ D. (SAQ A eligibility now also requires confirming the payment page is not susceptible to script-injection tampering — see Domain gates.)
  • Integer minor units only. All money is integer minor units (cents) + an explicit ISO-4217 currency code. No floating-point money math anywhere — not in totals, tax, discounts, or display conversion. Round at defined boundaries only.
  • Idempotency-key per charge (send side). Every create-charge / create-payment-intent / refund call carries a client-generated Idempotency-Key so a network retry, double-tap, or gateway timeout never double-charges. Keys are deterministic per logical operation and stored.
  • Signature-verified webhooks (receive side). Every inbound gateway webhook verifies the provider HMAC signature against the raw request body (Stripe Stripe-Signature / construct_event, Mollie fetch-by-id re-check, Adyen HMAC) before acting. Reject on failure. Then dedupe on event.id with a UNIQUE constraint, return 2xx fast (before heavy logic — Stripe fails a delivery after ~10s and retries for up to 3 days), and process the effect in a background/idempotent path. Tolerate duplicate and out-of-order events.
  • Test vs live separation. Test/sandbox keys are clearly separated from live; no live charge and no live-key touch without explicit owner approval (Forge honesty + irreversible-action rule). Real money is an owner-gated action, never autonomous.
  • Secrets in env + .env.example placeholders. No gateway secret, webhook signing secret, or API key in code, logs, error messages, or git.

Read the full file on GitHub · 44 lines

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. 5d ago First seen · 44 lines · 50 tokens per session scan A b00b86b26334

Subscribe to this mod's changes

forge-payments is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,438 once invoked, about $0.0003 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.