A runbook for testing x402 payments end to end on Base Sepolia, a public test network for the Base blockchain. It checks both a paid web route and a paid MCP tool through payment challenge, signing, retry, and response steps.

Use it to run the project’s payment smoke test, check paid HTTP routes and MCP tools, compare observed payment messages with the documented protocol, and report pricing drift.

It verifies that payment requests and responses still match the current x402 documentation and that tests cannot accidentally use mainnet funds or credentials.

How oyusypenko/rob-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to oyusypenko/rob-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/oyusypenko/rob-mcp/main/.claude/skills/x402-smoke/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/oyusypenko/rob-mcp

Made for: Claude Code.

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/skills/oyusypenko/rob-mcp/x402-smoke/github.svg)](https://agentmods.dev/skills/oyusypenko/rob-mcp/x402-smoke)

Your own site

<a href="https://agentmods.dev/skills/oyusypenko/rob-mcp/x402-smoke"><img src="https://agentmods.dev/badge/skills/oyusypenko/rob-mcp/x402-smoke/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/skills/oyusypenko/rob-mcp/x402-smoke"><img src="https://agentmods.dev/badge/skills/oyusypenko/rob-mcp/x402-smoke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00164	$0.01086
Opus 5	$0.00082	$0.00543
Sonnet 5	$0.00033	$0.00217
Haiku 4.5	$0.00016	$0.00109

Measured 11d ago against content hash ebf9a1bbc550, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

x402-smoke scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Boot: `bun run serve` (or against a deployed URL). `curl /healthz` → 200 with facilitator

.claude/skills/x402-smoke/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

x402 end-to-end smoke test (Base Sepolia)

Authoritative sources: docs/developers/architecture.md (x402 flow) and docs/developers/tools.md (PRICING — the prices this test must observe on the wire). Docs win; report drift.

Docs-first rule (mandatory, every run)

The @x402/* line moves fast. Before running, re-verify via context7 (resolve-library-id → query-docs) — @x402/fetch (client wrapper API), @x402/hono (middleware/challenge shape), @x402/mcp (paid-tool client) — and WebFetch the x402 quickstart at docs.cdp.coinbase.com as fallback. If the observed wire shape differs from the docs'd assumption, that IS the finding — flag before "fixing" the test.

Invariants this skill will not violate

Testnet only. X402_NETWORK=eip155:84532, facilitator https://x402.org/facilitator (D-24). Never point this at eip155:8453 mainnet or CDP credentials.
Throwaway wallet only. The paying key is a dedicated Base Sepolia test wallet (testnet USDC from the Circle faucet), stored in the local untracked .env as SMOKE_TEST_PRIVATE_KEY. It never holds mainnet funds, is referenced by NAME only, and lives exclusively in scripts/x402-smoke.ts — src/ must stay signing-free (no-custody rule; hook-enforced).
Read-only against the product — the smoke test buys data, changes nothing.

Procedure

Env: serve-mode .env with X402_NETWORK=eip155:84532, X402_PAY_TO=<test receive addr>, RPC_URL_4663 set; smoke wallet funded with Base Sepolia ETH-gasless USDC (EIP-3009 needs no gas from the payer; facilitator settles).
Boot: bun run serve (or against a deployed URL). curl /healthz → 200 with facilitator reachable.
Challenge shape: curl -i -X POST a paid /api/v1/tools/<tool-name> route with its JSON body → 402 with PAYMENT-REQUIRED carrying accepts that matches PRICING (scheme exact, network eip155:84532, correct price + payTo). Free tier: first FREE_CALLS_PER_DAY calls from a fresh IP return 200 WITHOUT payment; the 402 appears after.
Paid HTTP round-trip: bun scripts/x402-smoke.ts http — wraps fetch with the x402 client, asserts: 402 → PAYMENT-SIGNATURE retry → 200 + PAYMENT-RESPONSE, and the JSON payload validates against the tool's output schema.
Paid MCP round-trip: bun scripts/x402-smoke.ts mcp — connects the paid-MCP client to /mcp, calls one paid tool end-to-end, asserts a paid result (not a 402-in-result).
Verify settlement: the USDC transfer to X402_PAY_TO visible on Base Sepolia (sepolia.basescan .org) — amount equals the PRICING entry.

Read the full file on GitHub · 71 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.

11d ago First seen · 71 lines · 164 tokens per session scan A ebf9a1bbc550

Subscribe to this mod's changes

x402-smoke is a skill published in the GitHub repository oyusypenko/rob-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 1,086 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Testing Web3 and blockchain

web3-testing

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

wshobson/agents · 46 tokens

building-pydantic-ai-agents

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…

pydantic/pydantic-ai · 85 tokens

prompt-proximity-architecture

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…

elvisun/newsjack · 67 tokens

software-test-creation

Write failing tests for a TDD slice based on acceptance criteria and codebase conventions. Use when the "red" phase of red-green-refactor requires tests that define expected behavior before implementation exists. Discovers codebase test conventions first, writes test files that compile or parse but fail because the…

stencila/stencila · 82 tokens

tevm

Build, simulate, test, fork, and debug EVM transactions in TypeScript with tevm 1.0.0-rc.151. Use for in-process EVM scripts, typed Solidity imports, lazy mainnet or OP-stack forks, direct account and storage setup, viem-compatible contract actions, Vitest EVM tests, traces, and transaction simulation.

evmts/tevm · 77 tokens

verification-protocol

How to prove a hypothesis is TRUE or FALSE using Move unit tests.

PlamenTSV/plamen · 18 tokens

rob-mcp: Skill for Claude Code