wrxck-claude-plugins

Scaffold hardened MCP servers wrapping CLI tools

Create detailed Mermaid diagrams for architecture, flows, ERDs, and more

Enforce TypeScript quality - no any types, named exports, no console.log

Enforce React quality - accessibility, semantic HTML, no inline styles

Enforce Jest best practices - proper mock typing with jest.mocked()

C/C++ memory safety checks - smart pointers, safe string functions, RAII

Code style enforcement - comments, imports, file length, icons, TODOs, library choices

Security guards - prevent secret leaks and block sudo commands

Database safety - prevent accidental data destruction and migration safety

Docker quality and safety - Dockerfile best practices, compose validation, dangerous command blocking

Infrastructure security - nginx, port exposure, infra changes, env sync, hardening audits

Git workflow - commit validation, conventional commits, PRs, releases, code review

Deploy safety - smoke tests, perf regression detection, test gates, CI scaffolding

Package management - enforce exact versions, check outdated and vulnerable packages

Turns your corrections into enforceable hooks so Claude never repeats the same mistake

Ensures open source packages are properly released on npm, GitHub, and documented

Autonomous security auditor. Scans a GitHub repo for vulnerabilities, triages false positives, writes a PoC, fixes each confirmed bug in its own PR, independently reviews the fix, and merges when the review is clean.

Persistent Claude Code brain backed by Trilium / Obsidian / Notion. Standards, decisions, lessons learned, and per-app context that survive across sessions.

Mines how you actually use Claude Code and forges the work you keep repeating into the right artifact — skill, subagent, hook, command, workflow, or a publishable plugin. Local-only analysis; routes corrections to behavior-hooks, CLI-wrapping to mcp-forge, durable facts to matts-second-brain.