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 skills/zander-zyx/java-development-skill/java-development-skillnpx skills add zander-zyx/java-development-skill --skill java-development-skillgit clone --depth 1 https://github.com/zander-zyx/java-development-skillWhat 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 | $0.00102 | $0.02139 |
| Opus 5 | $0.00051 | $0.01069 |
| Sonnet 5 | $0.00020 | $0.00428 |
| Haiku 4.5 | $0.00010 | $0.00214 |
Grade A, and why
java-development 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Development Agent
Router skill for general Java/JVM work. Treat Spring Boot as one supported framework, not the default for every project. Load only the matching rule files below.
Defaults
- Output explanations in Chinese when the user uses Chinese; keep code unchanged unless editing.
- First identify the current project's runtime, Java version, build tool, framework, test stack, and conventions. Existing evidence beats this skill's defaults.
- Do not introduce Spring Boot, Maven, Gradle, Lombok, MyBatis-Plus, JPA, Testcontainers, or Java 17+ syntax unless the project already uses it or the user asks.
- If creating a new project and no preference is given: choose a dependency-supported Java LTS baseline (17 or newer), infer Maven or Gradle from the surrounding repository, use JUnit 5, constructor-based design, SLF4J-compatible logging, and immutable DTOs where practical.
- For a new Spring Boot project, verify the current stable release, Java/build requirements, and third-party starter compatibility from official sources before choosing a line. For existing projects, keep their supported line unless migration is requested.
- Do not choose a persistence framework by geography or popularity. Preserve the existing choice; for greenfield work, select JDBC, jOOQ, MyBatis/MyBatis-Plus, or JPA/Hibernate from the actual query model and team constraints.
- Prefer constructor injection in DI frameworks. Use Lombok (
@RequiredArgsConstructor,@Slf4j) only when the project already uses Lombok; otherwise write explicit constructors/loggers. - If multiple modules or frameworks exist, modify only the affected module unless the user asks for a cross-cutting change.
- Do not edit generated output unless explicitly requested; edit the source template, annotation processor input, schema, or generator configuration instead.
Loading Rules
Start with the smallest useful set:
- Any Java task: load
core/java-general-development.mdonly if project classification or default choice is unclear. - API/exception/version work: load the specific
core/...rule before framework rules. - Build edits: load exactly one build rule (
build-tools/...) matching the detected build tool. - Spring Boot edits: load the primary
spring-boot/...rule only when the project actually uses Spring Boot. - Broad code review: start with
code-review/cr-anti-patterns.md, then add specific risk files. - Test work: load
testing/test-layering.mdfirst, then the framework-specific test file. - JVM incident: load the symptom file first; add GC/thread/resource files only when evidence points there.
- Do not load README files or
examples/unless the user asks for usage docs.
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.
- yesterday First seen · 87 lines · 102 tokens per session scan A 0e39364a0e0e
java-development is a skill published in the GitHub repository zander-zyx/java-development-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 2,139 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
union-type-wrappers
Add typed getters and setters over BinaryData properties that represent TypeSpec union types in generated Java models. Use when generated classes expose BinaryData for union-typed fields and you need ergonomic, type-safe accessors instead.
run-tests
Run project tests using Maven (mvn). Use when the user asks to run tests.
search-m2
Search for Java classes inside Maven dependencies in /.m2. Use when the user asks to locate classes or inspect JARs. Cross-reference pom.xml files in the current directory to resolve dependency names/versions.
using-process-tool
Describes how to correctly use 'process' tool.
evergreen
Evergreen CI infrastructure, configuration validation. Use when modifying .evergreen/ config, preparing to submit changes or understanding the Evergreen test matrix.
create-package-skill
Interactive wizard that walks service teams through creating a package-specific skill for their Azure SDK package. Scans the package, detects customization patterns, scaffolds a SKILL.md with references, and validates with vally lint. The skill is placed inside the package's .github/skills/ directory so…