Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ccashwell/evm-cortexnpx agentmods add skills/ccashwell/evm-cortex/usdc-integrationWrote 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.
[](https://agentmods.dev/skills/ccashwell/evm-cortex/usdc-integration)<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/usdc-integration"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/usdc-integration/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.
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/usdc-integration"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/usdc-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.06804 |
| Opus 5.5 | $0.00030 | $0.02722 |
| Sonnet 5.5 | $0.00015 | $0.01361 |
| Haiku 4.5 | $0.00007 | $0.00680 |
Grade A, and why
usdc-integration 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 683 lines — stays where its author put it; the contents beside it link to each section on GitHub.
USDC Integration for Smart Contracts
The 6-Decimal Rule
USDC uses 6 decimals on every chain. Not 18. This is the single most common integration bug.
// 1 USDC = 1_000_000 (1e6)
uint256 constant USDC_UNIT = 1e6;
// $100 USDC
uint256 amount = 100 * 1e6; // 100_000_000
// $0.01 USDC (one cent)
uint256 oneCent = 1e4; // 10_000
// WRONG — this is 1 trillion USDC ($1,000,000,000,000)
uint256 catastrophic = 1e18;
Decimal Conversion
When protocols mix USDC (6 decimals) with 18-decimal tokens (WETH, DAI, most ERC-20s), explicit scaling is required:
uint256 constant SCALE_FACTOR = 1e12; // 18 - 6 = 12
// Scale 6 → 18 (lossless)
uint256 wad = usdcAmount * SCALE_FACTOR;
// Scale 18 → 6 (LOSES up to 1e12 - 1 wei of precision)
uint256 usdc = wadAmount / SCALE_FACTOR;
Never scale in a single arithmetic expression without isolating the conversion. Multiply before dividing to preserve precision:
// BAD — precision loss compounds
uint256 result = (usdcAmount * price) / 1e18;
// BETTER — scale USDC to 18 decimals first, then divide
uint256 result = (usdcAmount * SCALE_FACTOR * price) / 1e18;
// BEST — use a helper that makes intent explicit
uint256 result = _toWad(usdcAmount) * price / 1e18;
Production Contract Addresses
Mainnet — Native (Circle-issued) USDC
These are the canonical addresses issued directly by Circle via CCTP. All are FiatTokenV2_2 proxies.
| Chain | Address | Chain ID |
|---|---|---|
| Ethereum | 0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48 |
1 |
| Base | 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 |
8453 |
| Arbitrum One | 0xaf88d065e77c8cC2239327C5EDb3A432268e5831 |
42161 |
| Optimism | 0x0b2C639c533813f4Aa9D7837CAf62653d097Ff85 |
10 |
| Polygon PoS | 0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359 |
137 |
| Avalanche C-Chain | 0xB97EF9Ef8734C71904D8002F8b6Bc66Dd9c48a6E |
43114 |
| Solana | EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v |
— |
Testnet Addresses
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.
- 1mo ago First seen · 683 lines · 75 tokens per session scan A 96290a8e0343
usdc-integration is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 18d ago), licensed MIT. It adds 75 tokens to every session and 6,804 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…