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 skills add ApexIQ/skillsmith --skill java_expertgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/skills/apexiq/skillsmith/java_expert)<a href="https://agentmods.dev/skills/apexiq/skillsmith/java_expert"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/java_expert/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.
<a href="https://agentmods.dev/skills/apexiq/skillsmith/java_expert"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/java_expert.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00051 | $0.02118 |
| Opus 5.5 | $0.00020 | $0.00847 |
| Sonnet 5.5 | $0.00010 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
java-expert 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
☕ Java Expert — Production-Grade Java
Philosophy: Modern Java is not your grandfather's Java. Records, sealed classes, pattern matching, and virtual threads have transformed the language. Write modern Java, not enterprise Java from 2010.
1. When to Use This Skill
- Writing new Java services or libraries
- Reviewing Java code for modern patterns
- Building Spring Boot applications
- Working with JPA/Hibernate
- Configuring Maven or Gradle builds
- Writing tests with JUnit 5
2. Modern Java (17+)
Records Over Boilerplate Classes
// GOOD: Record — immutable, equals/hashCode/toString auto-generated
public record UserResponse(String id, String name, String email, Instant createdAt) {}
// GOOD: Record with validation
public record CreateUserRequest(String name, String email) {
public CreateUserRequest {
if (name == null || name.isBlank()) throw new IllegalArgumentException("name is required");
if (email == null || !email.contains("@")) throw new IllegalArgumentException("invalid email");
}
}
// BAD: 80-line POJO with getters, setters, equals, hashCode, toString, builder
public class UserResponse {
private String id;
private String name;
// ... 70 more lines of boilerplate
}
Sealed Classes for Domain Modeling
// GOOD: Sealed hierarchy — compiler knows all cases
public sealed interface PaymentResult permits Success, Failed, Pending {
record Success(String transactionId, BigDecimal amount) implements PaymentResult {}
record Failed(String reason, String errorCode) implements PaymentResult {}
record Pending(String pollUrl, Instant expiresAt) implements PaymentResult {}
}
// Pattern matching with exhaustive switch
String message = switch (result) {
case Success s -> "Paid $%s (tx: %s)".formatted(s.amount(), s.transactionId());
case Failed f -> "Failed: %s (%s)".formatted(f.reason(), f.errorCode());
case Pending p -> "Pending — check %s".formatted(p.pollUrl());
};
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 First seen · 291 lines · 51 tokens per session scan A 08da43b7c86d
java-expert is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 2,118 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
spring-boot-patterns
Spring Boot patterns including stereotype annotations, dependency injection, profiles, configuration properties, and actuator endpoints. Use when the user is building Spring Boot applications, configuring dependency injection, setting up profiles for different environments, using @ConfigurationProperties, or enabling…
java-spring
Build and upgrade Java/Spring services with explicit transaction, concurrency and deployment contracts. Use when implementing Spring Boot APIs, data access or jobs; verify JDK/framework/build-tool compatibility and preserve the application architecture.
quarkus-service-architecture
Use when building or extending a Java service with Quarkus - layered architecture, JAX-RS resources, CDI beans, Panache persistence, and native-friendly patterns.
spring-boot-fallback
Use when Java is chosen but Quarkus does not fit - build the service with Spring Boot using the same clean layering, only when a required library lacks a Quarkus extension or the repo already standardizes on Spring.
backend-language-decision
Use when starting a backend task that could be built in more than one language - follow the repository's stack, or for a greenfield service choose between Go, Java, C#/.NET, TypeScript on Node.js and Rust from the task's shape.
spring-boot-verify
Verify Spring Boot 4.x projects for correct dependencies, configuration, and migration readiness. Use when analyzing pom.xml, build.gradle, application.yml, discussing Spring Boot project setup, dependency versions, configuration validation, version compatibility, migration to Spring Boot 4, deprecated dependencies…