Plugin

mdbrain

A native Claude Code extension that prevents AI from over-refactoring your intentional code. Combines XML-structured protocols (BRAIN/CRAFT/PERF) with a 16-entry false-positive catalog, enforced by a five-layer Safety Net: permissions deny list, PreToolUse hook, tool-scoped subagents, path-scoped rules, and behavioral protocols. Coexists non-destructively with existing CLAUDE.md and memory/.

• Published source
• Repository

Analysed

11 October 2026

Last observed

12 October 2026

What the code does

• Runs hooks automatically Hooks that execute without being called explicitly.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.