agentlint

Name: agentlint
Author: mauhpr

mauhpr ★ 3

AgentLint is a guardrail engine for Claude Code that enforces 77 security and infrastructure rules across 8 configurable packs via hook-based checks on tool proposals, with denial of risky actions and guided correction feedback. The plugin integrates pre-tool, post-tool, and session hooks alongside three specialist agents for security audits, diagnostics, and policy fixes.

Security DevOps No API key detected runs shell

Install

> /plugin marketplace add mauhpr/agentlint-plugin

> /plugin install agentlint

Source: https://github.com/mauhpr/agentlint-plugin

What it's made of

2 commands · 3 agents · 1 MCP server · 6 hooks

Commands: 2
Agents: 3
Skills: 0
MCP servers: 1
Hooks: 6 · Notification, PostToolUse, PreToolUse, Stop, SubagentStop, UserPromptSubmit

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: agentlint-mcp resolve-and-run.sh
Talks to: nothing external detected

Analyzed 2026-11-02. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (mauhpr).