What is langchain4j-cdi CLAUDE.md?

A set of build and development instructions for LangChain4j CDI, a Java extension that lets Jakarta EE applications inject and configure LangChain4j AI services.

Use it when developing, building, testing, or reviewing LangChain4j CDI and its integration examples.

It explains the required Java versions, Maven commands, project modules, and exclusions needed to build and test the project correctly.

How langchain4j/langchain4j-cdi configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to langchain4j/langchain4j-cdi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/langchain4j/langchain4j-cdi/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/langchain4j/langchain4j-cdi

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/langchain4j/langchain4j-cdi/claude-md/github.svg)](https://agentmods.dev/instructions/langchain4j/langchain4j-cdi/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/langchain4j/langchain4j-cdi/claude-md"><img src="https://agentmods.dev/badge/instructions/langchain4j/langchain4j-cdi/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/langchain4j/langchain4j-cdi/claude-md"><img src="https://agentmods.dev/badge/instructions/langchain4j/langchain4j-cdi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,525 This file is loaded in full into every session.

When invoked 4,525 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.04525	$0.04525
Opus 5.5	$0.01810	$0.01810
Sonnet 5.5	$0.00905	$0.00905
Haiku 4.5	$0.00453	$0.00453

Measured 1mo ago against content hash 1b67af944da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

langchain4j-cdi 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 1mo 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 · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 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

LangChain4j CDI is a CDI (Contexts and Dependency Injection) extension that integrates the LangChain4j AI framework with Jakarta EE and Eclipse MicroProfile applications. It enables developers to inject AI services into CDI-managed beans with enterprise features like fault tolerance, telemetry, and external configuration.

Build System

CRITICAL: Use mvn command only - Never use ./mvnw or mvnw wrappers, as per user's global preferences.

Java Version Requirements:

Runtime target: Java 17
Build requirement: Java 21+ (some integration tests require Java 21+)

Payara Exclusion: Always exclude the Payara example module due to network connectivity issues:

-pl '!examples/payara-car-booking'

Essential Build Commands

Build and compile (skip tests):

mvn clean install -DskipTests -pl '!examples/payara-car-booking'

Full build with tests:

mvn clean verify -pl '!examples/payara-car-booking'

Run unit tests only (exclude integration tests):

mvn test -pl '!examples/payara-car-booking,!langchain4j-cdi-integration-tests'

Run all tests including integration:

mvn test -pl '!examples/payara-car-booking'

Check and apply code formatting:

mvn spotless:check -pl '!examples/payara-car-booking'
mvn spotless:apply -pl '!examples/payara-car-booking'

Module Architecture

Core Modules

langchain4j-cdi-core: Foundation of the CDI integration

@RegisterAIService stereotype annotation for declaring AI service interfaces
CommonAIServiceCreator utility for building AI service proxies from CDI beans
11 per-topology agent stereotype annotations (@RegisterSimpleAgent, @RegisterSequenceAgent, @RegisterLoopAgent, @RegisterParallelAgent, @RegisterParallelMapperAgent, @RegisterConditionalAgent, @RegisterSupervisorAgent, @RegisterPlannerAgent, @RegisterA2AAgent, @RegisterMcpClientAgent, @RegisterHumanInTheLoopAgent)
CommonAgentCreator utility for building agent proxies across all 11 topologies
AgentTopologyType enum defining available orchestration patterns
A2AAgentBuilder SPI for pluggable A2A topology implementation (loaded via ServiceLoader)
LLMConfig and LLMConfigProvider configuration API and SPI
CommonLLMPluginCreator for creating LangChain4j components via reflection
ExpressionResolver SPI for pluggable annotation attribute expression resolution

Read the full file on GitHub · 348 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.

1mo ago Changed · +3 tokens per session 1b67af944da7
1mo ago Changed · +4 lines · +638 tokens per session cdae5cc7f916
2mo ago First seen · 344 lines · 3,884 tokens per session scan A 09fc0d0ec220

Subscribe to this mod's changes

langchain4j-cdi CLAUDE.md is an instructions file published in the GitHub repository langchain4j/langchain4j-cdi (19 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,525 tokens to every session, about $0.0181 per session on Opus 5.5. 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 2026-09-01.

Backend and APIs Java Languages

langchain4j-cdi CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
langchain4j-cdi CLAUDE.mdlangchain4j/langchain4j-cdi	Instructions file	19	2d ago	Apache-2.0	A	4,525	Claude Code
graftcode graftcode-java.instructions.mdgrft-dev/graftcode	Instructions file	967	1mo ago	none	A	4,669	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

langchain4j-cdi: Instructions file for Claude Code