A command that analyses a project and sets up a complete payment integration, including the customer interface, server handling, database records and payment-provider webhooks. A webhook is an automatic message sent by one service to another after an event.

Detecting the project's setup, recommending a payment method, adding checkout and backend handling, processing webhook events, supporting refunds and providing a customer payment portal.

It provides a guided way to choose and implement payments while accounting for the project's technology and business needs.

start — Command for Claude Code by Hainrixz

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.

Clone the repo

git clone --depth 1 https://github.com/Hainrixz/agente-pagokit

Made for: Claude Code.

Or install pagokit, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 1 agent, 5 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hainrixz/agente-pagokit/start/github.svg)](https://agentmods.dev/commands/hainrixz/agente-pagokit/start)

Your own site

<a href="https://agentmods.dev/commands/hainrixz/agente-pagokit/start"><img src="https://agentmods.dev/badge/commands/hainrixz/agente-pagokit/start/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/hainrixz/agente-pagokit/start"><img src="https://agentmods.dev/badge/commands/hainrixz/agente-pagokit/start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 700 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.00700
Opus 5	$0.00012	$0.00350
Sonnet 5	$0.00005	$0.00140
Haiku 4.5	$0.00002	$0.00070

Measured 9d ago against content hash 2faf9dd1edfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

start 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.

commands/start.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are entering the PagoKit start flow.

Welcome the user briefly in their language (Spanish or English depending on the rest of their conversation):

🛒 PagoKit — voy a analizar tu proyecto y recomendarte el mejor método de pago. Después puedes correr /pagokit:doctor para auditar la integración o /pagokit:test para probar el webhook localmente.

(English equivalent if their messages are in English.)

Then proceed without further preamble:

Invoke the project-analyzer skill to detect stack, framework, deploy target, ORM, language, and use cases. Emit its structured JSON detection report in your reply (so the user sees what you saw), followed by the natural-language confirmation question.
Wait for the user to confirm or correct the detection (one round only — accept whatever they say and move on).
Invoke the payment-advisor skill to:
- Ask the 3 core questions (country + buyers, billing mode, local methods).
- Ask up to 2 conditional questions only if necessary.
- Apply hard filters + score ranking.
- Fall back to regions[country].fallback_cross_border_mor if no provider survives.
- Present top 1 recommendation with fee calculated in real money for a typical transaction in the user's product type.
- Cite last_verified_at as a disclaimer.
Wait for the user's selection — "sí / listo" to proceed, "muéstrame alternativas" for the next 1–2 options, or "pregunta" to dig in.
Delegate to the integration-specialist subagent once the user confirms. Pass the structured spec block (provider, stack, deploy_target, orm, billing_mode, frontend_style, required_methods, language, use_cases_detected, example_transaction_amount, example_currency).
Relay the subagent's final report to the user, plus a one-line legal-obligations footer based on detected region (GDPR / LGPD / LFPDPPP / CCPA / invoicing). Cite SECURITY_RULES Rule 11.
Suggest next steps:
- "Ejecuta /pagokit:test para validar el webhook localmente con un evento firmado."
- "Lee PAGOKIT_INTEGRATION.md para ver lo generado."
- "Antes de pasar a producción, revisa PAGOKIT_PRODUCTION_CHECKLIST.md."

Greenfield mode

If project-analyzer reports greenfield: true, skip step 2 (no detection to confirm) and add a question in step 3: "¿Qué planeas vender?". Then proceed.

Read the full file on GitHub · 50 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.

9d ago First seen · 50 lines · 24 tokens per session scan A 2faf9dd1edfd

Subscribe to this mod's changes

start is a command published in the GitHub repository Hainrixz/agente-pagokit (46 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 700 once invoked, about $0.0001 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.

Claude Code E-commerce Finance and fintech ai-agent claude-code-plugin latam lemon-squeezy mercado-pago

add-checkout

Create comprehensive shopping cart and checkout flow. Implement cart state management with Context API or Zustand. Create cart UI component with item list, quantity controls, and remove buttons. Calculate totals including subtotal, tax, shipping, and discounts. Add shipping address form with validation. Implement…

LarouexNonprofitConsulting/larouex-fullstack-plugin · 0 tokens

add-stripe

Integrate Stripe payment processing. Set up Stripe account and obtain API keys. Implement checkout flow using Stripe Checkout or Payment Element. Create payment API endpoints in Azure Functions or Express. Add webhook handling for payment events: succeeded, failed, refunded. Implement subscription billing with…

LarouexNonprofitConsulting/larouex-fullstack-plugin · 0 tokens

start

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Greenfield mode

What this file has done since we first saw it

Other commands, from other repositories

add-checkout

add-stripe

add-checkout

add-stripe

financial-model

research