Charge logo

Charge

Organization
runxhq
charge

Collect one exact payment on your selected Stripe, PayPal or x402 merchant account, with native approval and independent readback.

Overview

Publisherrunxhq
Repositoryrunx
Skill namecharge
Stars
105
Forks
109
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by runxhq on GitHub. Read the source before you install it.

Installation

Install the Charge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/runxhq/runx/tree/main/skills/charge
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/runxhq/runx.git /tmp/runx
mkdir -p .claude/skills
cp -r /tmp/runx/skills/charge .claude/skills/charge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Charge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Charge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Charge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Charge

Use charge when you are the seller and need to collect a payment. Choose the merchant connector explicitly: Stripe collects an existing payment method, PayPal captures a buyer-approved order, and Coinbase CDP settles the buyer's x402 authorization against its original quote. The selected connector instance fixes the account; an unavailable account never selects another method.

Run runx connector inspect <connector> to read the exact operation input schema. The default runner takes that public request, the connector name and a stable idempotency_seed. Its examples show each supported method. Provider-specific arguments stay with their owning connector, rather than becoming another payment API in the skill. Never supply card data, SPTs, wallet keys, API keys or bearer credentials. Credentials belong to the connector's configured custody.

Collect and confirm

Supply the exact account, amount, currency, reference and existing payment identifiers. The native operation owns admission, human approval, the provider request key, acknowledgement custody and readback. Stripe must independently return succeeded with the approved amount received; PayPal must independently return COMPLETED for the original merchant, order, amount and currency. The x402 lane retains its separate read of the original settled payment and returns the original quote, resource and settlement evidence. Incoming collection does not consume an outgoing spending allowance.

The result remains the selected provider's bounded native operation packet. Release the resource only when the exact payment is confirmed. A prepared order, buyer approval, submitted request, HTTP success or sealed plan does not establish settlement. Pending, refused, mismatched or unknown outcomes stop that release.

Prepare a buyer's payment

quote retains the x402 requirements for one exact resource and price; it takes no payment. checkout creates and independently reads one PayPal order and returns its buyer-action links. Creation is a provider mutation, not buyer approval or capture. Continue the approved order through the default PayPal collection lane with its original order identity and terms. Stripe collection requires an existing permitted payment method; this skill does not collect card details or impersonate the buyer. MPP purchase collection belongs to the existing purchase boundary and is not claimed as a standalone merchant lane here.

Continue safely

Stop on a missing binding, changed account or terms, denied approval, or uncertain readback. Resume or inspect the original native effect and payment identifiers; retain the original request key. A response lost after submission is not a reason to create another checkout, authorization, payment method or charge.

A buyer uses pay; invoice validation belongs to invoice-pay. To reverse a confirmed collection, use refund with its original processor, account, currency and payment reference. Those are separate governed actions and are not performed by this skill.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Charge AI skill do?

Collect one exact payment on your selected Stripe, PayPal or x402 merchant account, with native approval and independent readback.

Why use Charge on TypingMind?

Because you install it once and use it with any model. Charge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Charge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/runxhq/runx/tree/main/skills/charge. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Charge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Charge?

As many as you like. As long as a model supports skills, you can use Charge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Charge AI skill free?

Yes. It is published on GitHub by runxhq under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇