jabrena/plinth

Plinth is an AI-native engineering toolkit for modern Java enterprise SDLC, built around reusable Commands, Agents, Skills, and MCP Servers.

What it solves

Plinth for Java provides a structured, AI-native workflow for the Software Development Life Cycle (SDLC) of modern Java Enterprise applications. It aims to replace fragmented AI interactions with a standardized set of reusable skills, agents, and commands that guide developers through analysis, design, implementation, and operation of Java systems.

How it works

The project operates as a foundation for AI agents (such as Cursor, Claude Code, Codex, and GitHub Copilot) by providing a library of 125 skills, 9 agents, and 14 commands. It implements a specific workflow:

  1. Onboarding: Establishes repository guidance and project specifications.
  2. Analysis & Design: Uses commands like /explore-problem and /create-spec to turn ideas into functional and technical specifications.
  3. Build: Implements specifications using framework-aware delegation for tools like Spring Boot, Quarkus, and Micronaut.
  4. Operate: Coordinates Java profiling and benchmarking using tools like JMeter, Gatling, or JMH.
  5. Compliance: Provides skills to help engineers maintain awareness of regulations like the EU AI Act and GDPR.

Who it’s for

It is designed for software engineers working on Java Enterprise applications who want to integrate AI agents into their professional development workflow without sacrificing engineering judgment or architectural rigor.

Highlights

  • Comprehensive Java Ecosystem Support: Guidance for Maven, Spring Boot, Quarkus, Micronaut, and OpenAPI.
  • AI-Native Workflow: A predefined sequence of commands (from onboarding to closing specs) to manage the SDLC.
  • Extensive Skill Library: 125 specialized skills covering coding, testing, observability, and security.
  • Multi-Agent Compatibility: Works across various AI coding assistants including Cursor and Claude Code.
  • Cisco and NVIDIA Validated: Uses industry-standard scanners (Cisco AI Skill Scanner, NVIDIA SkillSpector) to ensure skill security and quality.

Related

  • Project
    ai-driven-dev/framework

    An enterprise-grade SDLC framework that integrates standardized workflows, skills, and agents into AI coding tools to automate the path from idea to pull request.

  • Project
    decebals/claude-code-java

    A collection of spec-compliant agent skills and templates that provide AI agents with domain knowledge and structured workflows for Java and Maven development.

  • Project
    openclaw/agent-skills

    OpenClaw Agent Skills is a reusable library of workflow “skills” (e.g., autoreview, behavior validation, session viewer) for AI coding agents in OpenClaw projects. It provides a Python installer to symlink or copy these skills into a user’s agent‑skill directory, enabling consistent, version‑controlled automation across repositories. Includes validation scripts, MIT licensing, and support for Codex/Claude agents.

  • Project
    microsoft/hve-core

    HVE Core is Microsoft’s open‑source, AI‑augmented SDLC framework. It ships VS Code and Copilot‑CLI plugins that expose specialised agents, prompt‑based instructions and reusable “skills” to automate research, planning, coding, security checks and review. The system encodes company‑wide standards and compliance rules, letting AI carry context while humans retain judgment. Teams install the extension, invoke the RPI (Research‑Plan‑Implement‑Review) agent, and can fork/customise the repo for their own processes.

  • Project
    coleam00/skills

    A library of 35 modular markdown-based skills and hooks for AI coding agents to standardize development workflows and reduce prompt bloat.