agentmods.dev

x402-verify-before-and-after-you-pay

x402-verify-before-and-after-you-pay is a skill for Claude Code, Codex from rezearcher/x402-data-api. It costs 125 tokens per session (1,275 once invoked), scanned A, original, MIT.

A payment-safety check for agents using x402, a system where an HTTP request can require payment, often with cryptocurrency. It checks an endpoint before payment and verifies the blockchain settlement afterward.

In plain words
What is it for?
Use it to receive a PAY, CAUTION, or AVOID decision before paying, then reconcile the recipient, amount, and settlement after payment.
Why use it?
It helps detect misleading prices, scam or sanctioned recipients, unsafe content, and payments that settle differently from what was promised.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo today A scan 125 tokens original MIT

Good fit Use it to receive a PAY, CAUTION, or AVOID decision before paying, then reconcile the recipient, amount, and settlement after payment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rezearcher/x402-data-api/clawhub-x402-verify
View source ↗ rezearcher/x402-data-api api.greyridgesignals.ai
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 rezearcher/x402-data-api --skill clawhub-x402-verify
Clone the repo
git clone --depth 1 https://github.com/rezearcher/x402-data-api

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 x402-verify-before-and-after-you-pay

README.md
[![agentmods](https://agentmods.dev/badge/skills/rezearcher/x402-data-api/clawhub-x402-verify/github.svg)](https://agentmods.dev/skills/rezearcher/x402-data-api/clawhub-x402-verify)
Your own site
<a href="https://agentmods.dev/skills/rezearcher/x402-data-api/clawhub-x402-verify"><img src="https://agentmods.dev/badge/skills/rezearcher/x402-data-api/clawhub-x402-verify/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 x402-verify-before-and-after-you-pay

Your own site · 80×15
<a href="https://agentmods.dev/skills/rezearcher/x402-data-api/clawhub-x402-verify"><img src="https://agentmods.dev/badge/skills/rezearcher/x402-data-api/clawhub-x402-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,275 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 $0.00125 $0.01275
Opus 5.5 $0.00050 $0.00510
Sonnet 5.5 $0.00025 $0.00255
Haiku 4.5 $0.00013 $0.00128

Measured today against content hash b22a59012e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

x402-verify-before-and-after-you-pay 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 today.

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.

integrations/clawhub-x402-verify/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify before and after you pay an x402 endpoint

An agent with a wallet can now pay any HTTP 402 endpoint on its own. Nothing in the x402 handshake tells it whether the endpoint is honest, whether the recipient is a sanctioned or drainer address, whether the advertised price is the price it will actually be charged, or — once it has paid — whether the money landed where it was promised. This skill closes both halves of that gap.

Two moments matter, and they are separate on-chain events with no shared state:

  • Before you pay — screen the endpoint and decide.
  • After you pay — prove the settlement matched what was advertised.

Pre-payment screeners cannot see the second half; a settlement can still go to the wrong recipient, be underpaid, or revert after a clean pre-pay screen. Do both.

1. Before you pay — screen the endpoint

Call the pre-flight check with the URL you are about to pay. One read-only request; it never spends. You get a single verdict plus the reasons behind it.

GET https://api.greyridgesignals.ai/x402/preflight?url=<endpoint-you-want-to-pay>

What it checks and returns (verdict: PAY | CAUTION | AVOID):

  • will it settle — validates the 402 challenge and accepts[]; labels liveness LIVE | ZOMBIE | DEAD.
  • safe to pay — screens payTo against the OFAC SDN list and a community scam/drainer set; scans the resource and any advertised MCP tools for LLM01 / LLM08 prompt-injection; flags an absolute price-trap (>= $1000 => AVOID).
  • price accuracy — live accepts[].amount vs the price the endpoint advertises: MATCH | OVERCHARGE | UNDERCHARGE.
  • delivery readiness — whether the paid resource is actually declared/served.

Decision rule for the agent:

  • PAY — proceed.
  • CAUTION — proceed only if the specific flagged reason is acceptable for this call.
  • AVOID — do not pay; pick another provider.

Try it free, no wallet, deterministic example:

GET https://api.greyridgesignals.ai/x402/preflight/preview

Read the full file on GitHub · 128 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. today First seen · 128 lines · 125 tokens per session scan A b22a59012e19

Subscribe to this mod's changes

x402-verify-before-and-after-you-pay is a skill published in the GitHub repository rezearcher/x402-data-api (0 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,275 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-11-05.

SecurityWeb3 and blockchainai-agentsbasecloudflare-workersdefimcpmcp-server
Related

Other skills, from other repositories

agentforge

Safety checks for agents that act on-chain. Call preflight once before any send, swap, approval, signature or x402 payment and get one proceed/caution/avoid verdict (transaction simulated, EIP-712 signature checked for permit phishing, recipients screened against OFAC sanctions and scam lists, tokens rug-checked).…

acarchidi/agentforge · 216 tokens

agentforge

Safety checks for agents that act on-chain. Call preflight once before any send, swap, approval, signature or x402 payment and get one proceed/caution/avoid verdict (transaction simulated, EIP-712 signature checked for permit phishing, recipients screened against OFAC sanctions and scam lists, tokens rug-checked).…

acarchidi/agentforge · 216 tokens

pantheon-staking

Stake creator coins into Pantheon vaults on Base and Robinhood Chain, view staking positions, and claim monthly rewards. Use when the user mentions Pantheon, pantheonvaults, staking a creator coin for yield, or checking/claiming Pantheon vault rewards.

BankrBot/skills · 59 tokens

delu-oracle

Full-cognition token analysis for Base EVM tokens via the deluagent oracle. Pass a CA or cashtag, get back a flat decision header (action, conviction, entry/stop/size, read) plus full cognition report. Tiered x402 pricing — 100M+ DELU free, 50M+ 50k DELU, public 250k DELU. Sequential calls only.

BankrBot/skills · 87 tokens

CTRL

Build on-chain automation on Base via CTRL - DCA, price-gated swaps, launchpad sniping, or whale-follow that run autonomously after one EIP-5792 wallet signature, bounded by preset caps.

aaronjmars/aeon-agent · 46 tokens

aero-vote-radar

Decide where to allocate sAERO on Aero (formerly Aerodrome) across its 7 networks, and check a wallet's stakes and 47 h timers. Use when someone asks which Aero pool pays best for their sAERO, how to split a stake, when they can move their allocation again, or what their current allocation earns. Read-only; never…

araxis33/aero-vote-radar · 84 tokens