Skip to main content
affpapa.org
RU EN
subagent

smart-contract-auditor — Claude Code subagent: features and install

Audits EVM and Solidity smart contracts for exploits, logic flaws, and economic attack vectors. Useful for pre-deployment reviews and vulnerability reports.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --agent blockchain-web3/smart-contract-auditor
Open on GitHub

What smart-contract-auditor does

This subagent inspects Solidity and EVM code to uncover access control flaws, reentrancy paths, and oracle manipulation risks. It runs shell tools, grep, and file lookups while classifying findings according to the OWASP framework. The agent reports problems without rewriting contract code or architecting upgrade schemes.

Audits cover token standard issues across ERC-4626, ERC-4337, and EIP-7702. The agent tests for flash loan exposures, proxy storage slot overlaps, and view-function read-only reentrancy. When needed, it runs static linters and Foundry property-based fuzz tests to confirm suspect execution paths.

The auditor never marks a repository as entirely safe to ship. If a working proof-of-concept exploit touches live public chains, the agent stops to confirm permission first.

What it helps with

  • Audit an ERC-4626 vault implementation for share inflation exploits
  • Detect reentrancy and permission bypasses in DeFi protocol contracts
  • Assess spot price dependencies against flash loan manipulation
  • Generate a structured risk report categorized by severity levels

Example prompts for the agent

  • Check my yield farming contract for reentrancy bugs and flash loan attack vectors.
  • Inspect this suspicious transaction on-chain to reveal the exploit mechanism.
  • Run a pre-deployment security review across all smart contracts in this repository.

How to install smart-contract-auditor

1claude-code-templates

npx claude-code-templates@latest --agent blockchain-web3/smart-contract-auditor

2Manually: put the files in place

.claude/agents/smart-contract-auditor.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about smart-contract-auditor

How do I install smart-contract-auditor in Claude Code?

Run npx claude-code-templates@latest --agent blockchain-web3/smart-contract-auditor in your terminal. This creates the configuration file at .claude/agents/smart-contract-auditor.md.

Does the agent fix the vulnerabilities it detects?

No, its scope is strictly restricted to uncovering bugs and documenting attack paths. Remediation code and architecture decisions are left to the developer.

Can this agent audit non-EVM networks like Solana?

Its primary toolchain and vulnerability checks are built specifically for EVM and Solidity. For non-EVM chains, it advises using ecosystem-specific tools instead.

Similar subagents

All subagents for Security →
code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. 31,050installs security-auditor official Anthropic This subagent searches code for security flaws and gives engineers concrete fixes. Use it to review a project before hardening or modernization work. 10,718installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. 9,715installs code-reviewer VoltAgent Community Reviews code changes for bugs, security flaws and maintenance issues. Use it before merging complex work or auditing a project. 31,050installs security-auditor VoltAgent Community Audits security controls, vulnerabilities, risks, and compliance gaps across systems, infrastructure, and processes. Use it when you need documented findings. 10,718installs devops-engineer VoltAgent Community This subagent reviews infrastructure and helps with CI/CD, containers, and deployment workflows. Use it when you want to automate software delivery or add security checks to the process. 7,392installs

From the same set495

The whole set →
ai-ethics-advisor This subagent reviews AI systems for bias, fairness problems, and regulatory gaps. Use it for ethics audits and responsible-AI documentation. 723installs bright-data-mcp This skill routes every web data task in Claude through the Bright Data MCP server instead of the built-in WebFetch and WebSearch. Useful when pages block bots or you want clean JSON. 722installs planning Keeps markdown files for goals, findings and session progress so an agent doesn't drift off the task mid-run. 712installs context7-auto-research This skill retrieves current library and framework references through the Context7 API. Use it when a Claude Code answer needs documentation for React, Next.js, Prisma, or another library. 709installs nextjs-performance-audit This command checks a Next.js project’s Lighthouse results, bundle size, and runtime performance. Use it to find performance issues and get optimization suggestions. 694installs agent-management This skill controls AI agents through the AI Maestro CLI, from creation and status checks to hibernation and plugin changes. Use it when several agents need lifecycle commands. 690installs figma-implement-design Turns a Figma node into code that fits your project: pulls the design context, a screenshot and assets over Figma MCP, then maps them onto your components and tokens. 689installs security-audit A workflow skill that walks a web app or API through recon, vulnerability scanning, pentesting, hardening and reporting. 673installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor