erc7702-patterns

erc7702-patterns is a skill for Claude Code, Codex from ccashwell/evm-cortex. It costs 53 tokens per session (1,616 once invoked), scanned A, original, MIT.

A guide to EIP-7702 account abstraction, which lets a regular blockchain account temporarily use smart-contract code without deploying a new account.

In plain words
What is it for?
Use it for transaction batching, sponsored transactions, session keys, delegated accounts, and decentralised-application integrations.
Why use it?
It enables smart-account behaviours while keeping the user's existing address, avoiding the separate infrastructure required by some other account-abstraction approaches.

Skill for Claude CodeCodex

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

Good fit Use it for transaction batching, sponsored transactions, session keys, delegated accounts, and decentralised-application integrations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccashwell/evm-cortex/erc7702-patterns
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 ccashwell/evm-cortex --skill erc7702-patterns
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex

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 erc7702-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc7702-patterns/github.svg)](https://agentmods.dev/skills/ccashwell/evm-cortex/erc7702-patterns)
Your own site
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/erc7702-patterns"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc7702-patterns/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 erc7702-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/erc7702-patterns"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc7702-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,616 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00053 $0.01616
Opus 5.5 $0.00021 $0.00646
Sonnet 5.5 $0.00011 $0.00323
Haiku 4.5 $0.00005 $0.00162

Measured 1mo ago against content hash 55daeb1f2298, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

erc7702-patterns 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.

skills/erc7702-patterns/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EIP-7702 Account Abstraction Patterns

Overview

EIP-7702 (shipped with Pectra, May 2025) lets EOAs temporarily delegate to smart contract code. The EOA's address gains smart contract capabilities without deploying a new account. Unlike EIP-4337, there's no separate EntryPoint or bundler infrastructure.

How It Works

A new transaction type (0x04) includes authorization tuples that set the EOA's code to point at a delegation contract:

authorization_list: [{ chain_id, address, nonce, y_parity, r, s }]

When the tx executes, the EOA's code is set to 0xef0100 || address (a delegation designator pointing to the implementation contract). All calls to the EOA now execute the implementation's code in the EOA's context.

Authorization Tuple

struct Authorization {
    uint256 chainId;   // 0 = valid on any chain
    address delegate;  // implementation contract
    uint64 nonce;      // EOA's current nonce
    uint8 yParity;
    bytes32 r;
    bytes32 s;
}

Sign offchain with the EOA's private key:

import { createWalletClient, http, parseEther } from 'viem';
import { mainnet } from 'viem/chains';
import { privateKeyToAccount } from 'viem/accounts';
import { eip7702Actions } from 'viem/experimental';

const account = privateKeyToAccount('0x...');
const client = createWalletClient({
  account,
  chain: mainnet,
  transport: http(),
}).extend(eip7702Actions());

const authorization = await client.signAuthorization({
  contractAddress: '0xDelegateContract...',
});

const hash = await client.sendTransaction({
  authorizationList: [authorization],
  to: account.address,
  data: encodeFunctionData({ ... }),
});

Delegation Contract (Smart Account)

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.27;

contract SmartAccount {
    struct Call {
        address target;
        uint256 value;
        bytes data;
    }

    /// @notice Execute a batch of calls from the delegating EOA.
    /// Only the EOA itself can invoke (msg.sender == address(this)).
    function execute(Call[] calldata calls) external payable {
        require(msg.sender == address(this), "Only self");
        for (uint256 i = 0; i < calls.length; i++) {
            (bool ok, bytes memory ret) = calls[i].target.call{value: calls[i].value}(calls[i].data);
            require(ok, string(ret));
        }
    }
}

Read the full file on GitHub · 214 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. 1mo ago First seen · 214 lines · 53 tokens per session scan A 55daeb1f2298

Subscribe to this mod's changes

erc7702-patterns is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 1,616 once invoked, about $0.0002 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.