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 vivekkachhadiyatech/skills --skill design-a-payment-flowgit clone --depth 1 https://github.com/vivekkachhadiyatech/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/vivekkachhadiyatech/skills/design-a-payment-flow)<a href="https://agentmods.dev/skills/vivekkachhadiyatech/skills/design-a-payment-flow"><img src="https://agentmods.dev/badge/skills/vivekkachhadiyatech/skills/design-a-payment-flow/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/vivekkachhadiyatech/skills/design-a-payment-flow"><img src="https://agentmods.dev/badge/skills/vivekkachhadiyatech/skills/design-a-payment-flow.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 | $0.00139 | $0.02671 |
| Opus 5 | $0.00069 | $0.01336 |
| Sonnet 5 | $0.00028 | $0.00534 |
| Haiku 4.5 | $0.00014 | $0.00267 |
Grade A, and why
design-a-payment-flow 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design a Payment Flow
When to use / when not to
- USE when you are designing a new money-movement path: taking a payment in, paying a party out, or moving funds across banks/currencies — and need to pick a rail, guarantee no double-charge, and reconcile.
- USE when integrating an external PSP (PayPal/Stripe/Adyen) and deciding callback vs polling, ledger shape, and settlement handling.
- NOT for a pure concept question ("what is interchange?", "how does SWIFT ACK work?") — read
../knowledge/payment-and-fintech.mddirectly instead. - NOT for the trading/e-commerce-catalog parts of the doc unless payment is the node in question.
Inputs to gather first
- Geography of payer and payee (US / India / cross-border / crypto) — drives the rail.
- Direction: pay-in, pay-out, or both (they are separate flows; see doc §7 money-movement).
- Latency need: instant vs next-day acceptable.
- Amount profile: low-value retail vs high-value; single vs many concurrent (hotspot risk).
- Same or different currency (FX needed?).
- Who holds balances: you (wallet/ledger) or only the PSP.
- Expected retry/failure surface (mobile clients, flaky networks).
Decision procedure
1. Select the rail (doc §1,4,5,6,12,13,16 — payment-system flows)
Pick by geography → speed → cost, using the doc's actual flows:
- Card / VISA (§1,2): global, cardholder-present or online. Real-time authorization (funds frozen) but money moves at end-of-day capture & settlement. Fee stack (§2): merchant discount fee = interchange ($1.75 of $100 to issuer) + acquiring markup ($0.25) + network assessment (VISA 0.11% + $0.0195/swipe). Use when you need broad acceptance and can tolerate deferred settlement.
- ACH (§4): US retail, batched, next-day (Same-Day ACH since 2018). Hard 7 PM Day-1 cut-off → operator (FedACH/EPN) clears ~midnight → RDFI credits 6 AM Day-2. Only banks initiate directly (via ODFI). Use for payroll/recurring low-value; never promise instant funds.
- UPI (§6): India, real-time. NPCI switch resolves a VPA (
bob@axis) → account across acquiring/issuing banks; PIN 2FA at issuer. Use for instant Indian retail with interoperability and no exposed account numbers. - SWIFT (§5): cross-border messaging, not money — store-and-forward with per-hop ACK/NAK (send) and UAK/UNK (delivery). Settlement rides a separate rail; reconcile the message trail against it. Use for international bank-to-bank.
- Wallet / scan-to-pay (§12,13): digital wallet + QR. Choose the mode from the 2×2: consumer- vs merchant-presented, dynamic vs static. Prefer dynamic QR (amount bound server-side, short-lived) for variable amounts; static QR is a cheap sticker but payer-enters-amount (error/fraud prone).
- Blockchain wallet (§16): one self-custody address, near-real-time on-chain confirmation, settlement = record (no end-of-day gap). Key management is the whole security surface.
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 · 114 lines · 139 tokens per session scan A 0743c7ab0e3b
design-a-payment-flow is a skill published in the GitHub repository vivekkachhadiyatech/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 2,671 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 2026-08-31.
Other skills, from other repositories
hps-y2k-chrome
OpenDesign's KPI decision brief: activation and retention drivers, what's working, and the one metric to move next. Built as a decision-grade data & finance deck for CRO, RevOps, leadership.
fsi-strip-profile
Creates professional investment banking strip profiles (company profiles) for pitch books, deal materials, and client presentations. Generates 1-4 information-dense slides with quadrant layouts, charts, and tables.
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.
business-design
Read financials, map competitive landscapes, and argue design decisions in the language of value. Use when defending design to commercial stakeholders. For the live negotiation itself, use design-negotiation (designer-toolkit).
fin-arch-diagram
A tool for creating architecture diagrams, process flowcharts, and hierarchy trees. These show how system parts, business steps, decisions, or organizational levels relate to one another.