Pay logo

Pay

Organization
runxhq
pay

Pay one exact resource with your held x402 wallet or approved Link MPP authorization, within the supplied terms and native authority.

Overview

Publisherrunxhq
Repositoryrunx
Skill namepay
Stars
105
Forks
109
Bundled files
5
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.

  • 5 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 Pay 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/pay
  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/pay .claude/skills/pay
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pay 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 Pay 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 Pay 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.

Pay

Use this when you are the buyer paying a known merchant resource. Choose the held connector explicitly: wallet/evm pays external x402 V2 with USDC on Base; link pays a Stripe MPP charge using an already approved one-time Link spend request. Stripe and PayPal merchant app credentials cannot spend as a buyer. Missing authority never selects another wallet or method.

Inspect the selected connector to construct its public request: the wallet's payment_signal, or Link's payment.mpp arguments. Supply the parent mandate's original term reference, exact resource URL, currency and maximum, plus a stable idempotency_seed. These purchase terms are checked before financial dispatch; they do not grant native authority. The native kernel still admits capability, run budget, human approval and the exact effect. No rounding or FX is implied.

x402 resource payment

The default composes settle once, readback and the terminal evidence check. The hosted wallet owns private signing, staged-byte recovery, on-chain finality and the paid resource result. A complete outcome requires a confirmed chain transaction and the resource's 2xx response; the resource's own product lifecycle may continue afterwards. Pending, failed or mismatched evidence never reports a completed purchase. Durable callers may use the x402-specific settle and readback runners separately and schedule later observations externally.

Link authorization and MPP payment

Install the pinned official Link CLI and bind the intended signed-in account with runx connector use link --session. Run authorize with the connector's spend.request arguments to request exact one-time wallet consent. Its approval URL/status is authorization evidence only; it does not prove payment. The connector binds consent to the original URL, method, body and challenge in Link metadata; an unrelated or unbound authorization is refused. Complete the wallet's approval, then supply that original spend request ID and original provider-issued MPP challenge to the default Link payment lane.

The connector pins and rechecks the account, amount/currency, payment method, merchant network and challenge. Only the official CLI retrieves the SPT; it never enters graph inputs, results or receipts. Independent original spend request readback must confirm the exact paid amount and transaction. This lane returns payment evidence, not the merchant HTTP body or delivery proof. Read a merchant artifact through its declared provider operation when needed. Link is not yet a selectable native paid-skill purchase method.

Continue the original effect

Stop on missing bindings, changed account/terms, denied approval or uncertain readback. Preserve the original effect, request key and provider references. Resume acknowledged effects at readback; never replace an ambiguous payment with another spend request, challenge, key or method. A refund already observed on Link cannot be presented as a fresh successful purchase.

Do not put wallet keys, SPTs, bearer tokens or card data in skill inputs. A paid Runx skill is bought by running that skill through the native purchase boundary; this job does not replace it. Use charge as the merchant, refund for an original collection's reversal, and invoice-pay to bind an invoice before pay.

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 Pay AI skill do?

Pay one exact resource with your held x402 wallet or approved Link MPP authorization, within the supplied terms and native authority.

Why use Pay on TypingMind?

Because you install it once and use it with any model. Pay 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 Pay in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/runxhq/runx/tree/main/skills/pay. 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 Pay?

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 Pay?

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

Is the Pay 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 👇