Bondterminal X402 logo

Bondterminal X402

Organization
NeverSight
bondterminal-x402

Query BondTerminal API using x402 keyless payments. No API key needed — pay $0.01 USDC per request on Base mainnet. Use when users ask for Argentine bond data, analytics, cashflows, history, riesgo país, or ISIN/ticker lookups (e.g. AL30, GD30, US040114HS26). Supports automatic 402 → payment → retry.

Overview

PublisherNeverSight
Repositorylearn-skills.dev
Skill namebondterminal-x402
Stars
210
Forks
38
Bundled files
12
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.

  • 12 bundled files

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

  • Open source

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

Installation

Install the Bondterminal X402 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.
  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/NeverSight/learn-skills.dev.git /tmp/learn-skills.dev
mkdir -p .claude/skills
cp -r /tmp/learn-skills.dev/data/skills-md/0juano/agent-skills/bondterminal-x402 .claude/skills/bondterminal-x402
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bondterminal X402 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 Bondterminal X402 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 Bondterminal X402 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.

BondTerminal x402

Query the BondTerminal API with x402 pay-per-call auth. No API key, no subscription — just sign and pay per request.

Cost: $0.01 USDC per request on Base mainnet.

API Endpoints

Base URL: https://bondterminal.com/api/v1

MethodEndpointDescriptionAuth
GET/treasury-curveUS Treasury yield curveFree
GET/bondsList all bonds (60+)x402
GET/bonds/:idBond details by ISIN or local tickerx402
GET/bonds/:id/analyticsPrice, YTM, duration, spreadsx402
GET/bonds/:id/cashflowsCashflow schedulex402
GET/bonds/:id/historyHistorical price/yield/spreadx402
POST/calculateBond analytics from custom pricex402
GET/riesgo-paisCurrent Argentina country riskx402
GET/riesgo-pais/historyHistorical riesgo país seriesx402
POST/calculate/batchBatch calculationsBearer only

Identifier formats: ISIN (US040114HS26), local ticker with D/C suffix (AL30D, GD30D).

Full docs: https://bondterminal.com/developers Endpoint reference in this skill: references/endpoints.md

How x402 Works

  1. Call any x402 endpoint without auth → server returns 402 with PAYMENT-REQUIRED header
  2. Decode the header (base64 JSON) to get payment requirements (amount, asset, network, payTo)
  3. Sign an EIP-3009 transferWithAuthorization via the x402 client library
  4. Retry the request with the signed payment in the PAYMENT-SIGNATURE header (v2), with X-PAYMENT as legacy fallback
  5. Server verifies payment via Coinbase facilitator, returns data + PAYMENT-RESPONSE header

Setup

1. Install dependencies

bash
npm install @x402/core @x402/evm viem

Note: The code examples use ES modules. Use .mjs file extension or add "type": "module" to your package.json.

2. Configure a signer

The x402 payment flow requires an EVM signer on Base mainnet with USDC balance. Configure your signer following the x402 EVM documentation.

The signer must implement { address, signTypedData } — any viem-compatible wallet client works (hardware wallet, KMS, injected provider, etc).

See references/signer-setup.md for a complete signer configuration example.

3. Register the x402 client

javascript
import { x402Client } from '@x402/core/client';
import { x402HTTPClient } from '@x402/core/http';
import { ExactEvmScheme } from '@x402/evm'; // exact export name

// signer = { address, signTypedData } — see references/signer-setup.md
const scheme = new ExactEvmScheme(signer);
const client = new x402Client();
client.register('eip155:8453', scheme); // Base mainnet
const httpClient = new x402HTTPClient(client);

Fetching Bond Data

javascript
async function fetchBT(path) {
  const url = `https://bondterminal.com/api/v1${path}`;
  let res = await fetch(url);

  if (res.status === 402) {
    const paymentRequired = httpClient.getPaymentRequiredResponse(
      (name) => res.headers.get(name),
      await res.json()
    );
    const payload = await httpClient.createPaymentPayload(paymentRequired);

    // Preferred v2 header
    res = await fetch(url, {
      headers: httpClient.encodePaymentSignatureHeader(payload),
    });

    // Legacy fallback for servers still expecting X-PAYMENT
    if (res.status === 402) {
      const encoded = Buffer.from(JSON.stringify(payload)).toString('base64');
      res = await fetch(url, { headers: { 'X-PAYMENT': encoded } });
    }
  }

  if (!res.ok) {
    throw new Error(`BondTerminal request failed (${res.status})`);
  }

  return res.json();
}

// Examples
const bonds = await fetchBT('/bonds');
const analytics = await fetchBT('/bonds/AL30D/analytics');
const riesgo = await fetchBT('/riesgo-pais');

Quick Test

Validate both free and paid flows:

javascript
await fetchBT('/treasury-curve'); // free route (no payment)
await fetchBT('/riesgo-pais');    // paid route (triggers x402 flow)

Wallet Requirements

The signing wallet needs:

  • USDC on Base — for the $0.01 payment per request

No ETH for gas is required — x402 uses EIP-3009 (off-chain signature), not on-chain transactions.

Notes

  • POST /calculate/batch requires a Bearer API key subscription — not available via x402
  • Local tickers require D/C suffix: AL30D (USD), AL30C (ARS) — not AL30
  • Settlement is on-chain: each paid call produces a verifiable transaction hash
  • The PAYMENT-RESPONSE header contains settlement metadata (payer, tx hash, network)

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 Bondterminal X402 AI skill do?

Query BondTerminal API using x402 keyless payments. No API key needed — pay $0.01 USDC per request on Base mainnet. Use when users ask for Argentine bond data, analytics, cashflows, history, riesgo país, or ISIN/ticker lookups (e.g. AL30, GD30, US040114HS26). Supports automatic 402 → payment → retry.

Why use Bondterminal X402 on TypingMind?

Because you install it once and use it with any model. Bondterminal X402 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 Bondterminal X402 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NeverSight/learn-skills.dev/tree/main/data/skills-md/0juano/agent-skills/bondterminal-x402. 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 Bondterminal X402?

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 Bondterminal X402?

As many as you like. As long as a model supports skills, you can use Bondterminal X402 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bondterminal X402 AI skill free?

It is published on GitHub by NeverSight. Check the repository for licensing terms. 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 👇