agentmods.dev

graalvm-expert

graalvm-expert is a skill for Claude Code, Codex from kinhluan/rules-quarkus-skills. It costs 39 tokens per session (870 once invoked), scanned A, original, MIT.

A specialised reference for GraalVM, a Java-based runtime that can also run other languages, including its Native Image compiler for building standalone programs.

In plain words
What is it for?
Answering questions about GraalVM Native Image, polyglot Java applications, reflection configuration, resource files, dynamic proxies, and native-build settings for Maven or Gradle projects.
Why use it?
It helps explain restrictions that appear when compiling JVM applications ahead of time, such as code loaded dynamically at runtime. It covers reflection, resources, proxies, startup initialisation, and memory management.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 3repo 3mo ago A scan 39 tokens original MIT

Good fit Answering questions about GraalVM Native Image, polyglot Java applications, reflection configuration, resource files, dynamic proxies, and native-build settings for Maven or Gradle projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kinhluan/rules-quarkus-skills/graalvm-expert
View source ↗ kinhluan/rules-quarkus-skills
Install

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.

Any agent
npx skills add kinhluan/rules-quarkus-skills --skill graalvm-expert
Clone the repo
git clone --depth 1 https://github.com/kinhluan/rules-quarkus-skills

Made for: Claude Code, Codex.

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.

agentmods badge for graalvm-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/kinhluan/rules-quarkus-skills/graalvm-expert/github.svg)](https://agentmods.dev/skills/kinhluan/rules-quarkus-skills/graalvm-expert)
Your own site
<a href="https://agentmods.dev/skills/kinhluan/rules-quarkus-skills/graalvm-expert"><img src="https://agentmods.dev/badge/skills/kinhluan/rules-quarkus-skills/graalvm-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.

agentmods 80×15 button for graalvm-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/kinhluan/rules-quarkus-skills/graalvm-expert"><img src="https://agentmods.dev/badge/skills/kinhluan/rules-quarkus-skills/graalvm-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 870 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00870
Opus 5 $0.00019 $0.00435
Sonnet 5 $0.00008 $0.00174
Haiku 4.5 $0.00004 $0.00087

Measured 12d ago against content hash 7eeeef8c0637, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

graalvm-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 12d 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.

.agent-skills/graalvm-expert/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

graalvm-expert

Keyword: graalvm | Platforms: gemini,claude,codex

High-Performance Polyglot & Native VM Expert Skill - Specialized in GraalVM AOT (Ahead-of-Time) compilation.

Core Mandates

  • AOT Mindset: Understand that Native Image has a "Closed-world assumption" (all bytecode must be known at build time).
  • Reflection Discipline: Mandate reflection-config.json for any dynamic class loading or reflection usage.
  • Initialization Policy: Differentiate between Build-time initialization (faster startup, smaller image) and Runtime initialization (safer for classes with side effects).
  • Polyglot Strategy: Leverage GraalVM SDK for high-performance interoperability between Java, JS, Python, and Ruby.

Native Image Mastery

  • Native Image Agent: Using java -agentlib:native-image-agent to automatically generate configuration files.
  • Resource Management: Config for resource-config.json to include static assets in the native binary.
  • Dynamic Proxy: Configuring proxy-config.json for Java dynamic proxies.
  • Substrate VM: Understanding memory management and GC options (G1 vs Serial) in native binaries.

GraalVM + Build Systems

  • Maven/Gradle: Using the GraalVM Native Build Tools plugins.
  • Bazel Integration: Configuring rules_graalvm and toolchains for hermetic native builds.
  • Quarkus Native: Troubleshooting Quarkus-specific native image failures (often related to extensions or transitive libraries).

Optimization & Performance

  • PGO (Profile-Guided Optimization): Collecting profiles from JIT runs to optimize AOT binaries.
  • Graal JIT: Using Graal as a replacement for C2 compiler in standard JVM mode for better performance in modern Java.
  • Static Analysis: Interpreting GraalVM build-time reports (reachability analysis).

Expert Tips

  • Always check reflect-config.json if you get ClassNotFoundException in a native binary.
  • Prefer quarkus.native.additional-build-args for passing low-level GraalVM flags.
  • Use --trace-class-initialization to debug complex initialization order issues.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 12d ago First seen · 66 lines · 39 tokens per session scan A 7eeeef8c0637

Subscribe to this mod's changes

graalvm-expert is a skill published in the GitHub repository kinhluan/rules-quarkus-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 870 once invoked, about $0.0002 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.

Claude CodeJavaLanguagesOptimizationagent-skillsai-agentsaotbazelbuild-systemgemini-cligraalvmjvmnative-imagepolyglot
Related

Other skills, from other repositories

neo4j-driver-java-skill

Neo4j Java Driver v6 — driver lifecycle, Maven/Gradle setup, executableQuery, executeRead/Write managed transactions, explicit transactions, async/reactive patterns, error handling, data type mapping, connection pool tuning, causal consistency/bookmarks. Use when writing Java or Kotlin code that connects to Neo4j via…

neo4j-contrib/neo4j-skills · 154 tokens

neo4j-spring-data-skill

Use when building Spring Boot applications with Neo4j using Spring Data Neo4j (SDN 7.x/8.x) — @Node entity mapping, @Relationship, @RelationshipProperties, Neo4jRepository, ReactiveNeo4jRepository, @Query annotations, application.yml configuration, projections, Neo4jClient, Neo4jTemplate, transactions, auditing, or…

neo4j-contrib/neo4j-skills · 148 tokens

java

Use when writing, reviewing or refactoring modern Java (21+, 25 LTS) — records and sealed interfaces as algebraic data types, exhaustive pattern-matching switch over instanceof ladders, virtual-thread concurrency, structured concurrency and ScopedValue replacing ThreadLocal, Stream and Optional pipelines…

ericrisco/rsc-harness · 89 tokens

java-expert

Expert-level Java development with Java 21+ features, Spring Boot, Maven/Gradle, and enterprise best practices. Use when the user mentions JVM, Spring, Maven, Gradle, or enterprise, or when the task involves Modern Java, Spring Boot, Build Tools, or Dependency Injection.

personamanagmentlayer/pcl · 63 tokens

coding-standards

Two thresholds apply — consider and enforce.

alexmond/jhelm · 21 tokens

scaffold-action

Generate a new jhelm action class and matching test file from a name.

alexmond/jhelm · 18 tokens