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 skills-il/tax-and-finance --skill pelecard-payment-gatewaygit clone --depth 1 https://github.com/skills-il/tax-and-financeWrote 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/skills-il/tax-and-finance/pelecard-payment-gateway)<a href="https://agentmods.dev/skills/skills-il/tax-and-finance/pelecard-payment-gateway"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/pelecard-payment-gateway/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/skills-il/tax-and-finance/pelecard-payment-gateway"><img src="https://agentmods.dev/badge/skills/skills-il/tax-and-finance/pelecard-payment-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00197 | $0.08881 |
| Opus 5.5 | $0.00079 | $0.03552 |
| Sonnet 5.5 | $0.00039 | $0.01776 |
| Haiku 4.5 | $0.00020 | $0.00888 |
Grade A, and why
pelecard-payment-gateway 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 9d 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pelecard Payment Gateway
Problem
Pelecard is a Payment Service Provider (PSP) that aggregates Israeli merchants onto the card acquirers over Shva, but its public documentation is scattered across a Postman workspace, a sandbox UI, a WordPress plugin listing and third-party PHP libraries, with no single canonical reference. Agents integrating Pelecard end up treating the hostname as an environment switch (it is not), inventing a refund endpoint that does not exist, picking the wrong ActionType (which silently changes whether money moves), or trusting a browser-side ConfirmationKey instead of re-verifying server-side. Each mistake leaks revenue or ships an exploitable "free order" path.
Overview
Card transactions clear on the Israeli Shva network (https://www.shva.co.il/, שב"א); Pelecard handles merchant onboarding, the iframe surface, tokenization and reconciliation on top. Your acquirer, not Pelecard, answers the PCI-tier and broadcast-policy questions below.
Pelecard's dominant integration is an iframe payment page: your server posts a credentials triple (terminal + user + password) plus the transaction parameters, gets back a URL and a ConfirmationKey, and redirects or embeds it. After the customer pays, Pelecard calls your server-side feedback URL. Store the Phase-1 ConfirmationKey keyed by your order; on the callback you MUST (a) match it byte-for-byte and (b) re-call PaymentGW/GetTransaction before treating the order as paid.
Pelecard has two server-to-server surfaces with different parameter-naming conventions.
/PaymentGW/* is the iframe surface and has exactly three endpoints. /services/* is where every
other operation lives: charges on a saved token, authorizations, voids, refunds, tokens, lookups, settlement,
3DS, invoices. Pelecard publishes a live request builder for them at
https://gateway21.pelecard.biz/services with a preset body for each; that page is the authoritative
endpoint reference, ahead of any third-party wrapper.
What ships with it
10 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.
- evidence.json 25 KB
- metadata.json 2.5 KB
- optimization-log.json 8.4 KB
- references/api-endpoints.md 13 KB
- references/domain-checklist.md 3.8 KB
- references/error-codes.md 36 KB
- references/payment-parameters.md 8.9 KB
- references/refunds-and-billing.md 7.0 KB
- scripts/validate_pelecard_response.py 19 KB runs code
- SKILL_HE.md 46 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.
- 9d ago Changed · +9 lines 1ebd260a7617
- 1mo ago First seen · 468 lines · 197 tokens per session scan A 6d3385b3ac5a
pelecard-payment-gateway is a skill published in the GitHub repository skills-il/tax-and-finance (38 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 8,881 once invoked, about $0.0008 per session on Opus 5.5. 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.
Other skills, from other repositories
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
snaplii-cli
Snaplii for Claude: buy discounted gift cards across 500+ brands with vouchers and up to 10% cashback, check the Snaplii Cash balance, pay bills (Canada) and send money to a phone number, through the snaplii MCP tools or the snaplii CLI, spending only the user's prepaid Snaplii Cash within the spending limit they set.…
stripe-payments
Add Stripe payments to a web app — Checkout Sessions, Payment Intents, subscriptions, webhooks, customer portal, and pricing pages. Covers the decision of which Stripe API to use, produces working integration code, and handles webhook verification. No MCP server needed — uses Stripe npm package directly. Triggers…
stripe
Stripe API integration with managed OAuth. Manage customers, subscriptions, invoices, products, prices, and payments. Use this skill when users want to process payments, manage billing, or handle subscriptions with Stripe. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).…
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…
shopify-admin-chargeback-watchlist-tagger
Identifies customers with disputed or charged-back orders and tags their customer record for proactive review on future orders.