xpay

xpay is a skill for Claude Code, Codex from xona-labs/xpay. It costs 83 tokens per session (2,459 once invoked), scanned A, original, MIT.

An agent wallet and payment tool for finding paid services and paying for them with USDC, a digital dollar-like currency, through the x402 payment system. It provides MCP tools, command-line access, and an SDK, and can create or reuse a Solana wallet.

In plain words
What is it for?
Finding a paid API, comparing its price and network, paying for and calling the service, sending USDC, checking the balance, and reviewing spending.
Why use it?
It handles service discovery, wallet use, payment, and network routing so the agent does not need custom payment code. This lets an agent call paid APIs when its wallet is funded.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions Codex.

Good fit Finding a paid API, comparing its price and network, paying for and calling the service, sending USDC, checking the balance, and reviewing spending.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xona-labs/xpay/xpay
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.

Any agent
npx skills add xona-labs/xpay --skill xpay
Clone the repo
git clone --depth 1 https://github.com/xona-labs/xpay

Made for: Claude Code, Codex.

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.

agentmods badge for xpay

README.md
[![agentmods](https://agentmods.dev/badge/skills/xona-labs/xpay/xpay/github.svg)](https://agentmods.dev/skills/xona-labs/xpay/xpay)
Your own site
<a href="https://agentmods.dev/skills/xona-labs/xpay/xpay"><img src="https://agentmods.dev/badge/skills/xona-labs/xpay/xpay/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.

agentmods 80×15 button for xpay

Your own site · 80×15
<a href="https://agentmods.dev/skills/xona-labs/xpay/xpay"><img src="https://agentmods.dev/badge/skills/xona-labs/xpay/xpay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,459 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.02459
Opus 5 $0.00042 $0.01229
Sonnet 5 $0.00017 $0.00492
Haiku 4.5 $0.00008 $0.00246

Measured 8d ago against content hash f1e7aa97b573, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

xpay 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 8d 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.

SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xona Wallet: a wallet and payment rail for agents

Xona Wallet lets an agent find a service, pay for it, and get the result without writing any payment plumbing. It hides x402, USDC, RPC, and multi-network routing behind a flat set of tools.

The fastest mental model: discover (find a paid service) → use (pay + call it) → you get the response. Or skip straight to do (find the best service for an intent and call it in one step).

Setup (zero-config)

Add Xona Wallet as an MCP server - no keys, no init:

{ "mcpServers": { "xpay": { "command": "npx", "args": ["-y", "@xona-labs/xpay", "mcp"] } } }

On first run the agent is given its own wallet. Its Solana address is printed to the server's stderr - fund that address with USDC and the agent can pay. The wallet persists and is reused across restarts.

To use a wallet you already hold instead, set XPAY_SOLANA_SECRET (base58) in the MCP env. To require an explicit wallet (no auto-generation), set XPAY_NO_AUTO_WALLET=1.

Tools

Tool Use it to
xpay_discover Find paid services by natural-language query. Returns ranked candidates with price, network, and payee.
xpay_use Pay for and call a specific service. Pass the full resource object from xpay_discover (preferred), or a resourceUrl. Handles the x402 402-challenge → pay → retry flow.
xpay_do One step: discover the best service for an intent and call it. Use when you don't need to compare options.
xpay_transfer Send USDC (or any Solana SPL token, or USDT0 on Stable) directly to an address. Executes immediately, gated by the user's guardrail - confirm amount + destination with the user before calling.
xpay_token_find Find Solana tokens by ticker, name, or mint (price, mcap, liquidity, verified flag). Read-only.
xpay_rwa_find List tradable RWA tokens on Solana: tokenized stocks/ETFs (xStocks, Ondo, Remora) + treasury-backed USDY. Free, read-only; results swappable via xpay_swap.
xpay_swap Swap tokens inside the wallet via Jupiter (Solana only). Irreversible; guardrail-gated. Confirm with the user first.
xpay_x_user Realtime X (Twitter) profile - followers, bio, verification. Paid (~$0.01 at cost via x402).
xpay_x_posts Recent posts from an X account with engagement metrics. Paid (~$0.06 at cost via x402).
xpay_shop_quote Free preflight for product search: exact price, marketplaces it would hit, and whether the query parses as a product search. Quote first when a query is ambiguous.
xpay_shop_search Product discovery across Google Shopping, Amazon, and eBay from one free-text query: normalized, deduped, ranked. Paid (~$0.02 via x402, less for fewer marketplaces).
xpay_balance The wallet's balance per network, plus its addresses (use this to tell the user where to send funds).
xpay_report Spending/income report (daily / weekly / monthly).
xpay_guardrail Read the active spending caps (per-tx, per-day, allowed hosts, approval threshold).
xpay_agenc_status Check the progress of an AgenC marketplace hire (see below). Read-only.
xpay_bento_status Check whether the Bento intent firewall is on (read-only).
xpay_bento_enable Turn the Bento intent firewall on. Returns the agent wallet address to register at app.bentoguard.xyz.
xpay_bento_disable Turn the Bento firewall off - use if the wallet isn't registered and payments are rejected.

Read the full file on GitHub · 165 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.

  1. 8d ago First seen · 165 lines · 83 tokens per session scan A f1e7aa97b573

Subscribe to this mod's changes

xpay is a skill published in the GitHub repository xona-labs/xpay (1 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 2,459 once invoked, about $0.0004 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 2026-08-31.