ccxt: Skill for Claude Code

.agents/skills/onchain-pay-open-api/SKILL.md

onchain-pay-open-api is a skill for Claude Code, Codex from ccxt/ccxt. It costs 193 tokens per session (4,975 once invoked), scanned C, original, MIT.

An API client for Binance Onchain Pay, which can buy cryptocurrency with fiat or send existing Binance funds directly to an external blockchain wallet. It also supports flows that move assets between blockchain networks.

In plain words
What is it for?
Use it to buy crypto and send it to a wallet, transfer existing Binance crypto to a friend or self-custody wallet, or arrange supported cross-chain transfers.
Why use it?
It combines payment, quoting, ordering, and wallet-transfer steps so an application can prepare these transactions through one service. Requests are signed automatically using RSA-SHA256.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is ccxt/ccxt's own configuration. It tells Claude Code and Codex how to work on ccxt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ccxt configures →

About the project

CCXT is a software library that gives programs a common interface for accessing cryptocurrency exchanges and prediction markets. It is used by developers, traders, analysts, and data scientists for market-data analysis, automated trading, backtesting, and trading bots.

ccxt/ccxt · 44,604 stars · on GitHub · docs.ccxt.com

Reuse

Borrowing it

Nothing to install: this file belongs to ccxt/ccxt. 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/ccxt/ccxt/master/.agents/skills/onchain-pay-open-api/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ccxt/ccxt

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 onchain-pay-open-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccxt/ccxt/onchain-pay-open-api/github.svg)](https://agentmods.dev/skills/ccxt/ccxt/onchain-pay-open-api)
Your own site
<a href="https://agentmods.dev/skills/ccxt/ccxt/onchain-pay-open-api"><img src="https://agentmods.dev/badge/skills/ccxt/ccxt/onchain-pay-open-api/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 onchain-pay-open-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccxt/ccxt/onchain-pay-open-api"><img src="https://agentmods.dev/badge/skills/ccxt/ccxt/onchain-pay-open-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,975 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high Privilege Escalation · line 102
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high System Prompt Leakage · line 367
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 $0.00193 $0.04975
Opus 5.5 $0.00077 $0.01990
Sonnet 5.5 $0.00039 $0.00995
Haiku 4.5 $0.00019 $0.00498

Measured 1mo ago against content hash ca7312670fd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

onchain-pay-open-api scanned grade C 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sign_and_call.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

### Step 1: Gather credentials
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/onchain-pay-open-api/SKILL.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Binance Onchain-Pay Open API Skill

Call Binance Onchain-Pay Open API endpoints with automatic RSA SHA256 request signing.

Use Cases & Scenarios

This skill is designed for the following scenarios:

1. 💳 Fiat-to-Crypto Purchase & Send

When to use: User wants to buy crypto with fiat currency and send directly to an external on-chain wallet address

  • Buy USDT with USD/EUR/TWD using credit card → Send to MetaMask address on BSC
  • Purchase BTC with Google Pay → Transfer to hardware wallet
  • Buy USDC with P2P → Send to DeFi protocol contract address

Key APIs: trading-pairs → payment-method-list → estimated-quote → pre-order

2. 🔄 Direct Crypto Transfer (Send Primary)

When to use: User has crypto in Binance account and wants to send to external address

  • Send existing USDT from Binance Spot to friend's wallet address
  • Transfer ETH to Uniswap contract for trading
  • Move crypto from Binance to self-custodial wallet (Trust Wallet, Ledger, etc.)

Key APIs: pre-order with SEND_PRIMARY customization

3. 🔗 Cross-Chain Bridge Operations

When to use: User needs to buy crypto on one chain and transfer to another network

  • Buy USDC on Ethereum → Bridge to Polygon for lower fees
  • Purchase tokens on BSC → Transfer to Base network
  • Fiat to crypto on Solana → Send to Arbitrum for DeFi

Key APIs: crypto-network → pre-order with network selection

4. 🏪 Merchant Payment Integration

When to use: Integrate crypto payment gateway for e-commerce or services

  • Accept fiat payments and auto-convert to crypto
  • Enable "Pay with Crypto" checkout flow
  • Process subscription payments with crypto

Key APIs: pre-order with externalOrderId tracking

5. 🤖 Smart Contract Interaction (Onchain-Pay Easy)

When to use: Buy crypto and execute smart contract in one transaction

  • Buy USDT and deposit to lending protocol
  • Purchase tokens and stake in DeFi pool
  • Fiat on-ramp directly to GameFi or NFT marketplace

Key APIs: pre-order with ON_CHAIN_PROXY_MODE customization

Read the full file on GitHub · 467 lines

Files

What ships with it

6 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. 1mo ago First seen · 467 lines · 193 tokens per session scan C ca7312670fd1

Subscribe to this mod's changes

onchain-pay-open-api is a skill published in the GitHub repository ccxt/ccxt (44,604 stars, last pushed today), licensed MIT. It adds 193 tokens to every session and 4,975 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.