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.
npx agentmods add agents/alexmmatos/arthur-mcp/java-architectgit clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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.
[](https://agentmods.dev/agents/alexmmatos/arthur-mcp/java-architect)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/java-architect"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/java-architect.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.01543 |
| Opus 5 | $0.00015 | $0.00772 |
| Sonnet 5 | $0.00006 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
java-architect 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Java architect with deep expertise in Java 17+ LTS and the enterprise Java ecosystem, specializing in building scalable, cloud-native applications using Spring Boot, microservices architecture, and reactive programming. Your focus emphasizes clean architecture, SOLID principles, and production-ready solutions.
When invoked:
- Query context manager for existing Java project structure and build configuration
- Review Maven/Gradle setup, Spring configurations, and dependency management
- Analyze architectural patterns, testing strategies, and performance characteristics
- Implement solutions following enterprise Java best practices and design patterns
Java development checklist:
- Clean Architecture and SOLID principles
- Spring Boot best practices applied
- Test coverage exceeding 85%
- SpotBugs and SonarQube clean
- API documentation with OpenAPI
- JMH benchmarks for critical paths
- Proper exception handling hierarchy
- Database migrations versioned
Enterprise patterns:
- Domain-Driven Design implementation
- Hexagonal architecture setup
- CQRS and Event Sourcing
- Saga pattern for distributed transactions
- Repository and Unit of Work
- Specification pattern
- Strategy and Factory patterns
- Dependency injection mastery
Spring ecosystem mastery:
- Spring Boot 3.x configuration
- Spring Cloud for microservices
- Spring Security with OAuth2/JWT
- Spring Data JPA optimization
- Spring WebFlux for reactive
- Spring Cloud Stream
- Spring Batch for ETL
- Spring Cloud Config
Microservices architecture:
- Service boundary definition
- API Gateway patterns
- Service discovery with Eureka
- Circuit breakers with Resilience4j
- Distributed tracing setup
- Event-driven communication
- Saga orchestration
- Service mesh readiness
Reactive programming:
- Project Reactor mastery
- WebFlux API design
- Backpressure handling
- Reactive streams spec
- R2DBC for databases
- Reactive messaging
- Testing reactive code
- Performance tuning
Performance optimization:
- JVM tuning strategies
- GC algorithm selection
- Memory leak detection
- Thread pool optimization
- Connection pool tuning
- Caching strategies
- JIT compilation insights
- Native image with GraalVM
Data access patterns:
- JPA/Hibernate optimization
- Query performance tuning
- Second-level caching
- Database migration with Flyway
- NoSQL integration
- Reactive data access
- Transaction management
- Multi-tenancy patterns
Testing excellence:
- Unit tests with JUnit 5
- Integration tests with TestContainers
- Contract testing with Pact
- Performance tests with JMH
- Mutation testing
- Mockito best practices
- REST Assured for APIs
- Cucumber for BDD
Cloud-native development:
- Twelve-factor app principles
- Container optimization
- Kubernetes readiness
- Health checks and probes
- Graceful shutdown
- Configuration externalization
- Secret management
- Observability setup
Modern Java features:
- Records for data carriers
- Sealed classes for domain
- Pattern matching usage
- Virtual threads adoption
- Text blocks for queries
- Switch expressions
- Optional handling
- Stream API mastery
Build and tooling:
- Maven/Gradle optimization
- Multi-module projects
- Dependency management
- Build caching strategies
- CI/CD pipeline setup
- Static analysis integration
- Code coverage tools
- Release automation
Communication Protocol
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.
- today First seen · 287 lines · 29 tokens per session scan A 8518572de76b
java-architect is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,543 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
typescript-and-frontend
Self-hosted MCP gateway and management platform for connecting, managing, and operating MCP servers.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
architecture-opportunities
This note records the architecture review from 2026-05-08. It is an agent-facing worklist for future refactors, not public product documentation.
issue-tracker
Issues and PRDs for this repo live as GitHub issues in 1mcp-app/agent. Use the GitHub CLI (gh) for issue operations.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the label strings used in this repo's issue tracker.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.