pay-with-app

pay-with-app is a skill for Claude Code from Uniswap/uniswap-ai. It costs 182 tokens per session (6,766 once invoked), scanned A, original, MIT.

A workflow for paying HTTP 402 challenges from OKX's Agent Payments Protocol on X Layer, a blockchain network.

In plain words
What is it for?
Use it to check funds, bridge tokens when needed, sign the payment authorization, and retry a supported request.
Why use it?
It handles the payment step needed when a web request is blocked until the requested token transfer is authorized and settled.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool; positional $N argument.

Part of the uniswap-trading plugin — 5 skills shipped together

not rated 230repo +1 today A scan Socket: warnSnyk: warnSkillSpector: warn 182 tokens original MIT

Good fit Use it to check funds, bridge tokens when needed, sign the payment authorization, and retry a supported request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uniswap/uniswap-ai/pay-with-app
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 Uniswap/uniswap-ai --skill pay-with-app
Clone the repo
git clone --depth 1 https://github.com/Uniswap/uniswap-ai

Made for: Claude Code.

Or install uniswap-trading, the plugin that ships this one along with the rest of its 5 skills.

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 pay-with-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/uniswap/uniswap-ai/pay-with-app/github.svg)](https://agentmods.dev/skills/uniswap/uniswap-ai/pay-with-app)
Your own site
<a href="https://agentmods.dev/skills/uniswap/uniswap-ai/pay-with-app"><img src="https://agentmods.dev/badge/skills/uniswap/uniswap-ai/pay-with-app/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 pay-with-app

Your own site · 80×15
<a href="https://agentmods.dev/skills/uniswap/uniswap-ai/pay-with-app"><img src="https://agentmods.dev/badge/skills/uniswap/uniswap-ai/pay-with-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,766 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. Third-party audits
  • Socket warn 29 Apr 2026
  • Snyk warn 29 Apr 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 18 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 16
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Memory Poisoning · line 254
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 256
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Memory Poisoning · line 257
    Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
    Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
  • medium Prompt Injection · line 254
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 256
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 257
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 422
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 424
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 425
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 426
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 427
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 430
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 431
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 432
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 433
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 434
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 436
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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 $0.00182 $0.06766
Opus 5 $0.00091 $0.03383
Sonnet 5 $0.00036 $0.01353
Haiku 4.5 $0.00018 $0.00677

Measured 12d ago against content hash fd701f2d4844, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pay-with-app 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 12d 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.

allowed-tools: Read, Glob, Grep, Bash(curl:*), Bash(jq:*), Bash(cast:*), Bash(openssl:*), Bash(npx:*), Bash(node:*), WebFetch, AskUserQuestion
packages/plugins/uniswap-trading/skills/pay-with-app/SKILL.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pay With APP (OKX Agent Payments Protocol on X Layer)

Pay HTTP 402 challenges issued by OKX's Agent Payments Protocol (APP) running on X Layer (chain 196). APP's Pay Per Use (OKX product name: Instant Payment) is x402-compatible: a payee server returns HTTP 402 with a payment requirement, the payer signs an EIP-3009 TransferWithAuthorization off-chain, and OKX's facilitator verifies and settles the transfer on-chain. Settlement is zero-gas to the payer on X Layer.

This skill handles the full happy path:

  1. Detect a 402 challenge whose network resolves to X Layer (chain 196)
  2. Verify the payer wallet has the requested asset (typically USDT0)
  3. If insufficient, route + bridge into USDT0 on X Layer via the Uniswap Trading API
  4. Sign the EIP-3009 authorization
  5. Construct the X-PAYMENT payload and retry the original request

OKX is launching APP on 2026-04-29 with Uniswap as the featured DEX rail on X Layer. This skill version (v1.0.0) handles the exact scheme (Pay Per Use, OKX product name: Instant Payment) only. Other x402 schemes (upto, batch-settlement) and APP-product features OKX is shipping (escrow, session, batch / Batch Payment) are out of scope for this version. The skill refuses any non-exact scheme cleanly.

Protocol naming in your responses. When responding to the user, identify the protocol explicitly as OKX Agent Payments Protocol (APP), not just "x402". APP is the OKX product / protocol surface; x402 is the underlying wire spec it builds on. Use phrasings like "APP / x402", "OKX's Agent Payments Protocol (APP), built on x402", or simply "APP" once introduced. Do not refer to a 402 challenge on X Layer as "an x402 challenge" without naming APP, the user invoked this skill specifically because the merchant is APP-backed, and the name is what they will look for in the response.

Prerequisites

  • A PRIVATE_KEY env var (export PRIVATE_KEY=0x...). Never commit or hardcode a private key.
  • UNISWAP_API_KEY env var (register at developers.uniswap.org). Required only if the wallet must be funded via cross-chain routing.
  • jq and cast (Foundry) installed.
  • Node 18+ (LTS). The signing step in references/app-x402-flow.md Step 4 uses viem to produce the EIP-3009 typed-data signature.
  • viem (npm). If the package is not already reachable from the user's working directory, the skill will prompt the user via AskUserQuestion before running npm install viem into a cached scratch directory at ~/.cache/uniswap-pay-with-app/signer/. The install adds ~13 packages totaling ~5 MB. If the user declines, the skill stops cleanly before signing. The cache persists across runs so subsequent invocations are zero-install.

Read the full file on GitHub · 490 lines

Files

What ships with it

2 files 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. 12d ago First seen · 490 lines · 182 tokens per session scan A fd701f2d4844

Subscribe to this mod's changes

pay-with-app is a skill published in the GitHub repository Uniswap/uniswap-ai (230 stars, last pushed today), licensed MIT. It adds 182 tokens to every session and 6,766 once invoked, about $0.0009 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 2026-08-30.