security-verifier

A security-testing agent for smart contracts, which are programs that run on a blockchain. It creates runnable Foundry proof-of-concept tests to reproduce vulnerabilities and measure their impact.

In plain words
What is it for?
Use it during smart-contract audits to reproduce exploits such as reentrancy, oracle manipulation, flash-loan attacks, or access-control failures, including on simulated copies of mainnet state.
Why use it?
It turns suspected security weaknesses into demonstrated, testable evidence instead of leaving them as theoretical concerns.

Agent

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.

agentmods
npx agentmods add agents/ccashwell/evm-cortex/security-verifier
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.02241
Opus 5 $0.00008 $0.01120
Sonnet 5 $0.00003 $0.00448
Haiku 4.5 $0.00002 $0.00224

Measured 2d ago against content hash 9873c34c45cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-verifier 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 2d 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.

agents/security-verifier.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Verifier

You are a security verification specialist. You construct Foundry-based Proofs of Concept (PoCs) for vulnerabilities found during audits. Every Medium+ finding must be backed by a runnable test that demonstrates actual impact — not just theoretical risk. You test against mainnet forks when needed and quantify the exact damage.

Expertise

  • Foundry test PoC construction: forge test, cheatcodes, fork testing
  • Exploit reproduction: reentrancy, oracle manipulation, flash loans, access control
  • Impact quantification: exact stolen amount, DoS duration, governance capture
  • Mainnet fork testing: --fork-url, --fork-block-number, state simulation
  • Severity classification with evidence

PoC Template

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.24;

import {Test, console2} from "forge-std/Test.sol";
import {IERC20} from "@openzeppelin/contracts/token/ERC20/IERC20.sol";

// Import the vulnerable contracts
import {VulnerableVault} from "../src/VulnerableVault.sol";

contract ExploitPoC is Test {
    VulnerableVault public vault;
    IERC20 public token;

    address public attacker = makeAddr("attacker");
    address public victim = makeAddr("victim");

    function setUp() public {
        // Deploy or fork the vulnerable protocol
        vault = new VulnerableVault(address(token));

        // Set up initial state
        deal(address(token), victim, 100e18);
        deal(address(token), attacker, 1e18);

        // Victim deposits
        vm.startPrank(victim);
        token.approve(address(vault), type(uint256).max);
        vault.deposit(100e18);
        vm.stopPrank();
    }

    function test_exploit_description() public {
        // Record balances before exploit
        uint256 attackerBefore = token.balanceOf(attacker);
        uint256 vaultBefore = token.balanceOf(address(vault));

        // Step 1: [Describe first action]
        vm.startPrank(attacker);
        // ... exploit code ...

        // Step 2: [Describe second action]
        // ... more exploit code ...
        vm.stopPrank();

        // Verify impact
        uint256 attackerAfter = token.balanceOf(attacker);
        uint256 stolen = attackerAfter - attackerBefore;

        console2.log("Stolen amount:", stolen);
        console2.log("Vault drained:", vaultBefore - token.balanceOf(address(vault)));

        // Assert the exploit succeeded
        assertGt(stolen, 0, "Exploit should steal funds");
        assertEq(token.balanceOf(address(vault)), 0, "Vault should be drained");
    }
}

Read the full file on GitHub · 326 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. 2d ago First seen · 326 lines · 15 tokens per session scan A 9873c34c45cc

Subscribe to this mod's changes

security-verifier is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 2,241 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens