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/alexmond/jhelm/coding-standardsnpx skills add alexmond/jhelm --skill coding-standardsgit clone --depth 1 https://github.com/alexmond/jhelmWhat 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 | $0.00021 | $0.01590 |
| Opus 5 | $0.00010 | $0.00795 |
| Sonnet 5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
coding-standards 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jhelm Coding Standards
Style
- Indentation: Tabs (enforced by
spring-javaformat-maven-plugin) - Naming: Classes
PascalCase, methods/variablescamelCase, constantsUPPER_SNAKE_CASE - Javadoc: HTML tags for links,
{@code true}/{@code false}for booleans, accurate@param/@returntags
Lombok
@Getter/@Setterfor simple fields,@Datafor POJOs/DTOs@Builder,@NoArgsConstructor,@AllArgsConstructorfor complex objects@Slf4jfor logging@Accessors(fluent = true)for internal DSL-like classes
Modern Java 21
- Text blocks (
"""...""") for multi-line strings - Enhanced switch (arrow syntax)
- Streams/Lambdas for collection manipulation
- try-with-resources for system resource streams (e.g.,
Files.walk())
Error Handling
- SLF4J via
@Slf4j— noSystem.out.printlnin production code (CLI output injhelm-cliis the exception) - Descriptive exceptions; always include original cause when rethrowing
- Prefer
must*function variants when strict validation is required
Dependencies
- Manage versions in root
pom.xml<dependencyManagement> - Define dependency versions as properties in root
pom.xml<properties>(unless managed by Spring Boot parent) - Keep
jhelm-gotemplatefree of Spring dependencies
Size Guidelines
Two thresholds apply — consider and enforce:
| Scope | Consider refactoring | Checkstyle enforces (build fails) |
|---|---|---|
| File | > 500 lines | > 800 lines |
| Method | > 50 lines | > 80 lines |
Consider (500 lines / 50 lines): A warning signal. Before adding more code to a large file or method, ask whether it should be split. Extract helpers, separate concerns, or move related methods to a dedicated class.
Enforce (1000 lines / 80 lines): Hard limit. The build fails at validate phase. Refactoring is required — no exceptions except the suppressions below.
Current suppressions (checkstyle-suppressions.xml):
Lexer.java,Parser.java— state machines; long methods are inherent to the patternHelmChartTemplates.java— methods return static YAML text blocks, not logic*Test.java— test files are exempt from both size limits
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.
- 2d ago First seen · 148 lines · 21 tokens per session scan A 374d2a99ca17
coding-standards is a skill published in the GitHub repository alexmond/jhelm (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,590 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 2026-08-31.
Other skills, from other repositories
quarkus-backend
Use this skill when building Quarkus backend applications — supersonic Java, Dev UI, GraalVM native, reactive messaging, Panache ORM. This skill enforces: compile-time metadata processing, live reload, continuous testing, container-first design. Do NOT use for: Spring Boot projects, Micronaut applications, standard…
effective-java
Generate and review Java code using patterns and best practices from Joshua Bloch's "Effective Java" (3rd Edition). Use this skill whenever the user asks about Java best practices, API design, object creation patterns, generics, enums, lambdas, streams, concurrency, serialization, method design, exception handling, or…
java-expert
Expert knowledge for Modern Java (21+) development, including Virtual Threads, performance tuning, and idiomatic clean code. Use for deep Java language/logic questions.
graalvm-expert
Expert knowledge for GraalVM, Native Image (AOT), Polyglot runtime, and reflection/resource configuration. Use for native compilation and multi-language JVM questions.
java-kotlin
Java and Kotlin programming patterns.
mcp-java-dev-tools-bug-drill
Discover bounded Java method drill candidates or run a Probe-guided diagnostic drill for one selected method and return an evidence-backed Markdown report.