seojoonkim

Agentlinter — Security skill for Claude Code

Security community

ESLint for AI Agents — AGENTS.md/CLAUDE.md 채점·진단·자동수정 Position Risk Warning · Token Efficiency · Security Check.

How to install Agentlinter

This entry records only its repository, not the path inside it, so there is no exact command to give. Open seojoonkim/agentlinter and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agentlinter does

ESLint for AI Agents — AGENTS.md/CLAUDE.md 채점·진단·자동수정 Position Risk Warning · Token Efficiency · Security Check.

Alternatives in Security

Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
Fp Check — Trail of Bits security skill for fp check 3.7k ★
Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★

README

🧬 AgentLinter

ESLint for AI Agents — Score, diagnose, and auto-fix your entire agent workspace.
Free & open source. Always will be.

Website · Quick Start · Scoring · Comparison · How it Works

GitHub Stars

Why AgentLinter?

Your AI agent is only as good as its config files. A vague `CLAUDE.md` produces vague results. A leaked API key becomes a vulnerability. Contradictions across files cause unpredictable behavior.

*"Be specific: 'Use 2-space indentation' is better than 'Format code properly.'"* — [Anthropic, CLAUDE.md Best Practices](https://code.claude.com/docs/en/memory)

**AgentLinter treats your agent config as code** — scanning, scoring, and fixing it with the same rigor you'd apply to source code.

The problems it solves

Problem	Impact	AgentLinter
🔇 Vague instructions fail silently	"Be helpful" gives zero guidance	Detects ambiguity, suggests specifics
🔑 Secrets in plain text	API keys committed to repos	Scans for 20+ secret patterns