DevoxxGenieIDEAPlugin CLAUDE.md

Repository instructions for DevoxxGenie, a Java plugin for IntelliJ IDEA that connects the editor to local and cloud-based language models. It describes threading rules and the required development workflow.

In plain words
What is it for?
Use it when changing the IntelliJ plugin, especially its user interface, background tasks, model integrations, web search, tool servers, or agent features.
Why use it?
It helps prevent frozen editor windows and unsafe UI updates while enforcing the project's branch and investigation practices.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/devoxx/devoxxgenieideaplugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/devoxx/DevoxxGenieIDEAPlugin
Per session 1,285 This file is loaded in full into every session.
When invoked 1,285 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01285 $0.01285
Opus 5 $0.00642 $0.00642
Sonnet 5 $0.00257 $0.00257
Haiku 4.5 $0.00128 $0.00128

Measured 2d ago against content hash c9dfed81a1c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DevoxxGenieIDEAPlugin CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

DevoxxGenie is a Java-based LLM Code Assistant plugin for IntelliJ IDEA that integrates with both local LLM providers ( Ollama, LMStudio, GPT4All, Llama.cpp, Exo) and cloud-based LLMs (OpenAI, Anthropic, Mistral, Groq, Gemini, DeepInfra, DeepSeek, OpenRouter, Azure OpenAI, Amazon Bedrock). The plugin supports advanced features like RAG (Retrieval-Augmented Generation), MCP (Model Context Protocol) servers, web search, and agentic programming capabilities.

Threading Constraints

This is a JetBrains/IntelliJ plugin. UI operations must run on the EDT (Event Dispatch Thread), and long-running operations must NOT block it. Use ApplicationManager.getApplication().invokeLater() or ReadAction/WriteAction as appropriate.

Workflow Rules

When asked to investigate or fix an issue, do NOT deeply explore the entire codebase autonomously. Start focused on the specific area mentioned, and ask before expanding scope. Avoid unnecessary web searches unless explicitly requested.

Git Workflow

Always create a feature/fix branch BEFORE making any code changes. Never edit code on the current branch without confirming the branch strategy first. Feature/fix branches for issues are cut from develop (e.g. fix/issue-1234).

Testing

When asked to investigate a bug, write a reproducing test FIRST — confirm it fails — before applying any fix, unless told otherwise.

Build & Development Commands

Java Version Requirement

IMPORTANT: This project requires JDK 21 for building. JDK 25 causes Gradle build script failures. Always set JAVA_HOME before running Gradle commands:

export JAVA_HOME=~/.sdkman/candidates/java/21-zulu

Testing

IMPORTANT: Always pipe test output to grep for failures so you can immediately focus on what failed:

./gradlew test 2>&1 | grep -E "FAILED|failed"
./gradlew test --tests ClassName 2>&1 | grep -E "FAILED|failed"
./gradlew test --tests ClassName.methodName 2>&1 | grep -E "FAILED|failed"
./gradlew verifyPlugin                            # Verify plugin (includes tests)

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 136 lines · 1,285 tokens per session scan A c9dfed81a1c1

Subscribe to this mod's changes

DevoxxGenieIDEAPlugin CLAUDE.md is an instructions file published in the GitHub repository devoxx/DevoxxGenieIDEAPlugin (677 stars, last pushed 6d ago), licensed MIT. It adds 1,285 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.