guard-x402-payments

guard-x402-payments is a skill for Codex from razel369/intentfence. It costs 89 tokens per session (1,144 once invoked), scanned A, original, Apache-2.0.

A safety procedure for x402 payments, where a web service asks an agent to pay before access is granted. It checks the exact payment quote against spending and payee rules before signing.

In plain words
What is it for?
Inspecting a payment-required challenge, checking the target URL, method, price, and payee, and allowing or rejecting the payment; an exact assessment costs 0.005 USDC on Base.
Why use it?
It can block payments that exceed a price limit or target an unapproved merchant, while keeping signing keys local and producing policy evidence.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Inspecting a payment-required challenge, checking the target URL, method, price, and payee, and allowing or rejecting the payment; an exact assessment costs 0.005 USDC on Base.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/razel369/intentfence/guard-x402-payments
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 razel369/intentfence --skill guard-x402-payments
Clone the repo
git clone --depth 1 https://github.com/razel369/intentfence

Made for: 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 guard-x402-payments

README.md
[![agentmods](https://agentmods.dev/badge/skills/razel369/intentfence/guard-x402-payments/github.svg)](https://agentmods.dev/skills/razel369/intentfence/guard-x402-payments)
Your own site
<a href="https://agentmods.dev/skills/razel369/intentfence/guard-x402-payments"><img src="https://agentmods.dev/badge/skills/razel369/intentfence/guard-x402-payments/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 guard-x402-payments

Your own site · 80×15
<a href="https://agentmods.dev/skills/razel369/intentfence/guard-x402-payments"><img src="https://agentmods.dev/badge/skills/razel369/intentfence/guard-x402-payments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,144 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 $0.00089 $0.01144
Opus 5 $0.00044 $0.00572
Sonnet 5 $0.00018 $0.00229
Haiku 4.5 $0.00009 $0.00114

Measured 10d ago against content hash 58dfa6566a65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

guard-x402-payments 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 10d 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.

skills/guard-x402-payments/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guard x402 Payments

Use the live IntentFence service to inspect the exact x402 quote the caller observed. Keep signing keys local and treat the result as policy evidence, not as permission to spend.

Choose the check

  • For a real x402 quote, use the paid exact-quote assessment. It costs 0.005 USDC on Base per successful assessment.
  • For a declared action without a PAYMENT-REQUIRED challenge, use the free, unsigned preview. Do not describe a preview as verified or settled.
  • If the caller has not authorized the 0.005 USDC assessment fee, show the fee and stop before signing or submitting payment.

Assess an exact quote

  1. Make the intended request without payment and capture the complete base64 PAYMENT-REQUIRED header, exact target URL, and HTTP method.
  2. Define policy.max_price_usdc. Add every approved merchant address to policy.allowed_payees; without an explicit matching payee, a quote cannot receive safe_to_proceed.
  3. Call the MCP tool intentfence_x402_assessment at https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp, or POST the same input to https://agentpass-protocol.rmalka06.chatgpt.site/api/x402-assessments?utm_source=agent_skill&utm_medium=agent&utm_campaign=guard_x402_payments:
{
  "subject": "agent:buyer-07",
  "target_url": "https://merchant.example/paid-resource",
  "method": "GET",
  "payment_required": "BASE64_PAYMENT_REQUIRED_HEADER",
  "policy": {
    "max_price_usdc": "0.10",
    "allowed_payees": ["0x1111111111111111111111111111111111111111"]
  }
}
  1. Expect IntentFence's own x402 challenge. Have the caller's x402 client sign it locally only after fee authorization, then retry the unchanged request with PAYMENT-SIGNATURE or the MCP payment metadata required by that client.
  2. Accept a completed assessment only when the response is successful and includes the decision, signed receipt, and x402 settlement evidence. The service fee settlement does not prove that the merchant was paid or that it will deliver.

Read the full file on GitHub · 111 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 111 lines · 89 tokens per session scan A 58dfa6566a65

Subscribe to this mod's changes

guard-x402-payments is a skill published in the GitHub repository razel369/intentfence (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,144 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.

Related

Other skills, from other repositories