erc8004-patterns

erc8004-patterns is a skill for Claude Code, Codex from ccashwell/evm-cortex. It costs 49 tokens per session (1,812 once invoked), scanned A, original, MIT.

A set of patterns for giving blockchain-based AI agents an onchain identity, declared capabilities, and trust relationships using ERC-8004.

In plain words
What is it for?
Use it when registering agents, declaring their capabilities, authenticating interactions, or building trust between agents and onchain protocols.
Why use it?
It helps other agents and blockchain programs verify who an agent is, what it can do, and who controls it.

Skill for Claude CodeCodex

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

Good fit Use it when registering agents, declaring their capabilities, authenticating interactions, or building trust between agents and onchain protocols.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccashwell/evm-cortex/erc8004-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 erc8004-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 erc8004-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc8004-patterns/github.svg)](https://agentmods.dev/skills/ccashwell/evm-cortex/erc8004-patterns)
Your own site
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/erc8004-patterns"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc8004-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 erc8004-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/erc8004-patterns"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/erc8004-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,812 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 $0.00049 $0.01812
Opus 5.5 $0.00020 $0.00725
Sonnet 5.5 $0.00010 $0.00362
Haiku 4.5 $0.00005 $0.00181

Measured 17d ago against content hash 0c272defb41d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

erc8004-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 17d 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/erc8004-patterns/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ERC-8004 Onchain Agent Identity

Overview

ERC-8004 establishes a standard for AI agent identity onchain. Deployed on January 29, 2026 across 20+ chains, it provides a registry for agents to declare their identity, capabilities, and trust relationships. This enables verifiable agent-to-agent and agent-to-protocol interactions.

Core Interface

interface IERC8004 {
    struct AgentIdentity {
        address agent;         // agent's onchain address (EOA or contract)
        bytes32 identityHash;  // hash of offchain identity metadata
        uint64 registeredAt;
        uint64 expiresAt;
        address operator;      // human or org that controls the agent
        uint8 trustLevel;      // 0-255 trust score
    }

    struct Capability {
        bytes32 capabilityId;  // keccak256 of capability name
        bytes params;          // ABI-encoded capability parameters
    }

    event AgentRegistered(address indexed agent, bytes32 identityHash, address indexed operator);
    event AgentRevoked(address indexed agent, address indexed revokedBy);
    event CapabilityDeclared(address indexed agent, bytes32 indexed capabilityId);

    function registerAgent(AgentIdentity calldata identity, Capability[] calldata capabilities) external;
    function revokeAgent(address agent) external;
    function getIdentity(address agent) external view returns (AgentIdentity memory);
    function getCapabilities(address agent) external view returns (Capability[] memory);
    function isRegistered(address agent) external view returns (bool);
    function hasCapability(address agent, bytes32 capabilityId) external view returns (bool);
    function verifyAgent(address agent, bytes32 requiredCapability) external view returns (bool);
}

Registry Integration

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.20;

import {IERC8004} from "./interfaces/IERC8004.sol";

contract AgentGatedProtocol {
    IERC8004 public immutable agentRegistry;
    bytes32 public constant TRADE_CAPABILITY = keccak256("trade");
    bytes32 public constant REBALANCE_CAPABILITY = keccak256("rebalance");

    modifier onlyRegisteredAgent() {
        require(agentRegistry.isRegistered(msg.sender), "Not a registered agent");
        _;
    }

    modifier requiresCapability(bytes32 capId) {
        require(agentRegistry.verifyAgent(msg.sender, capId), "Missing capability");
        _;
    }

    constructor(address registry_) {
        agentRegistry = IERC8004(registry_);
    }

    function executeTrade(bytes calldata tradeData)
        external
        onlyRegisteredAgent
        requiresCapability(TRADE_CAPABILITY)
    {
        // Agent-executed trade logic
    }

    function rebalanceVault()
        external
        onlyRegisteredAgent
        requiresCapability(REBALANCE_CAPABILITY)
    {
        // Only agents with rebalance capability
    }
}

Read the full file on GitHub · 233 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. 17d ago Changed · +5 lines 0c272defb41d
  2. 1mo ago First seen · 228 lines · 49 tokens per session scan A 9a2a0b8fb245

Subscribe to this mod's changes

erc8004-patterns is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 49 tokens to every session and 1,812 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.