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 ArabAgentSkills/arab-payments-skill-atlas --skill mena-payment-guardiangit clone --depth 1 https://github.com/ArabAgentSkills/arab-payments-skill-atlasWrote 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/arabagentskills/arab-payments-skill-atlas/mena-payment-guardian)<a href="https://agentmods.dev/skills/arabagentskills/arab-payments-skill-atlas/mena-payment-guardian"><img src="https://agentmods.dev/badge/skills/arabagentskills/arab-payments-skill-atlas/mena-payment-guardian/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/arabagentskills/arab-payments-skill-atlas/mena-payment-guardian"><img src="https://agentmods.dev/badge/skills/arabagentskills/arab-payments-skill-atlas/mena-payment-guardian.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 | $0.00091 | $0.01641 |
| Opus 5 | $0.00046 | $0.00821 |
| Sonnet 5 | $0.00018 | $0.00328 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
mena-payment-guardian 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.
MENA Payment Guardian
Mission
Use this skill for Arab/MENA payment and BNPL integrations where redirects, webhook delivery, signature validation, capture timing, local currencies, and duplicate events can break production. Provider references are source-linked field notes; official provider docs and merchant agreements remain the authority for endpoint-level details.
Decision Path
Always follow this order:
- Identify the provider, country, integration path, payment method, and environment.
- Load the matching provider reference and shared pattern.
- Confirm the server boundary and list secret env var names only.
- Verify the authenticity signal: HMAC, signature, SecureHash, webhook secret, encrypted webhook payload, static auth header, or documented server-side inquiry.
- Compare order reference, provider reference, amount, currency, country/account context, and status.
- Store provider events and provider transaction references idempotently before fulfillment.
- Fulfill only from verified server-side state.
- Add tests or manual QA for duplicate events, invalid signatures, delayed callbacks, stale failures, capture/refund/void misuse, and frontend secret exposure.
Non-Negotiables
- Treat all money movement as high risk.
- Never fulfill from a browser redirect, hosted checkout result, SDK callback, BNPL approval page, or frontend-only status alone.
- Verify provider signatures, HMACs, SecureHash values, webhook secrets, encrypted payloads, or documented server-side inquiry exactly as documented.
- Keep merchant credentials, HMAC secrets, server keys, secret API keys, access codes, terminal secrets, SHA phrases, and service role keys server-side only.
- Compare provider amount, currency, country/account context, local order reference, and provider transaction/reference before creating paid state.
- Make callbacks, webhooks, retries, inquiry responses, capture calls, refunds, voids, and page refreshes idempotent.
- Store provider event/reference uniqueness before activating subscriptions, enrollments, bookings, credits, shipments, or invoices.
- Do not overwrite a stronger final paid/captured state with older pending, failed, cancelled, expired, rejected, or duplicate signals.
- Log safe identifiers only: local order id, provider reference, status, event id, timestamp. Never log tokens, card data, signatures, HMAC secrets, API keys, access codes, SHA phrases, or raw credentials.
What ships with it
42 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.
- evals/scenarios/adapter-mena-routing.md 970 B
- evals/scenarios/amazon-payment-services-sha-feedback.md 1.2 KB
- evals/scenarios/amount-currency-country-mismatch.md 952 B
- evals/scenarios/bnpl-authorize-capture-confusion.md 1.4 KB
- evals/scenarios/capture-refund-void-misuse.md 980 B
- evals/scenarios/duplicate-callback-retry.md 1.0 KB
- evals/scenarios/frontend-secret-exposure.md 1.0 KB
- evals/scenarios/gated-doc-endpoint-invention.md 1013 B
- evals/scenarios/hyperpay-partial-approval.md 1.4 KB
- evals/scenarios/hyperpay-resourcepath-status-query.md 1.1 KB
- evals/scenarios/moyasar-card-auth-webhook-events.md 1.5 KB
- evals/scenarios/moyasar-secret-token-authorized.md 1022 B
- evals/scenarios/myfatoorah-refund-status-webhook.md 1.3 KB
- evals/scenarios/myfatoorah-webhook-get-payment-details.md 1.0 KB
- evals/scenarios/paytabs-return-ipn-signature.md 1.1 KB
- evals/scenarios/redirect-only-rejection.md 967 B
- evals/scenarios/signature-verification-required.md 1.0 KB
- evals/scenarios/tabby-country-webhook-capture-race.md 1.6 KB
- evals/scenarios/tabby-dispute-refund-window.md 1.3 KB
- evals/scenarios/tamara-pre-check-eligibility.md 1.3 KB
- evals/scenarios/tap-authorize-capture-method-support.md 1.1 KB
- references/patterns/capture-refund-void-lifecycle.md 1.4 KB
- references/patterns/idempotency-state-transitions.md 1.4 KB
- references/patterns/private-docs-policy.md 887 B
- references/patterns/server-secret-boundary.md 1.1 KB
- references/patterns/webhook-first-fulfillment.md 1.0 KB
- references/provider-index.json 18 KB
- references/providers/amazon-payment-services.md 4.2 KB
- references/providers/easykash.md 4.1 KB
- references/providers/fawrypay.md 4.1 KB
- references/providers/geidea.md 4.3 KB
- references/providers/hyperpay.md 5.5 KB
- references/providers/kashier.md 3.5 KB
- references/providers/moyasar.md 5.8 KB
- references/providers/myfatoorah.md 5.6 KB
- references/providers/paymob.md 5.4 KB
- references/providers/paysky.md 3.5 KB
- references/providers/paytabs.md 4.4 KB
- references/providers/tabby.md 7.1 KB
- references/providers/tamara.md 7.1 KB
- references/providers/tap-payments.md 5.0 KB
- references/providers/valu-souhoola.md 3.9 KB
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 · 91 tokens per session scan A d865fc26270b
mena-payment-guardian is a skill published in the GitHub repository ArabAgentSkills/arab-payments-skill-atlas (4 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 1,641 once invoked, about $0.0005 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
stock-analyzer
Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
saas-billing
Implement and audit SaaS billing systems, subscription state machines, secure webhooks, and local database synchronization / Implementasi dan audit sistem billing SaaS, state machine langganan, webhook aman, dan sinkronisasi database lokal.
payment-gateway-expert
Expert guide for integrating payment gateways (Stripe, PayPal, Xendit, Midtrans, DOKU) and secure webhooks into SaaS platforms / Panduan ahli integrasi payment gateway dan webhook aman.
doku-mcp-server
Expert guide for DOKU Model Context Protocol (MCP) Server integration. Enables AI Agentic Commerce with tools for payment links, Virtual Accounts, QRIS, transaction status checks, and client configuration (Claude Desktop, Cursor, AGY) / Panduan ahli DOKU MCP Server untuk AI Agentic Commerce.
tray-pagamentos
API de informações de pagamento da Tray (recurso payments). Cobre listar, consultar, criar, atualizar e excluir registros de pagamento (CRUD em /payments), além de consultar as opções de pagamento ativas da loja (/payments/options) e as configurações globais de pagamento (/payments/settings). Total de 7 endpoints.…