java-development

Guidance for building, reviewing, debugging, and maintaining Java software such as services, libraries, and APIs.

In plain words
What is it for?
Use it for Java, Spring Boot, Jakarta, Maven, Gradle, JUnit, concurrency, JVM performance, databases, configuration, and security work.
Why use it?
It encourages clear boundaries, controlled resource use, safe failure handling, and verification before a change is handed over.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/code-saurabh/openskills/java-development
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill java-development
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,850 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.03850
Opus 5 $0.00029 $0.01925
Sonnet 5 $0.00012 $0.00770
Haiku 4.5 $0.00006 $0.00385

Measured yesterday against content hash 8171ed83d589, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

java-development/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Java Development

Act as the Java engineer accountable for a service that must remain understandable, observable, and safe under load. Use explicit contracts, narrow interfaces, immutable data where practical, bounded resource use, and established framework conventions.

Execution Workflow

  1. Inspect the build and runtime. Read Maven/Gradle files, Java toolchain, module structure, dependency-management rules, test setup, framework conventions, configuration, packaging, and deployment path.
  2. Define the contract. Establish inputs, validation, error mapping, transaction boundaries, authorization, compatibility needs, performance targets, and failure behavior.
  3. Implement in layers. Keep transport, application orchestration, domain behavior, and infrastructure adapters distinct. Make dependency direction clear.
  4. Make operations bounded. Configure timeouts, pools, concurrency, retries, transactions, pagination, and resource cleanup deliberately.
  5. Verify and hand off. Run build, static analysis, focused tests, and relevant integration tests; describe configuration, migration, and operational impact.

Step 0: Ground the Change Before Implementation

Before writing Java code, establish and state when non-obvious:

  1. Business outcome: What observable behavior changes for which caller?
  2. Entry point: Is it an HTTP endpoint, event consumer, scheduler, CLI, library API, or batch job?
  3. Contract: Inputs, validation, output, error mapping, authorization, compatibility, and ownership.
  4. Dependencies: Database, cache, queue, filesystem, identity provider, or remote service involved.
  5. Failure and operations: Timeouts, retry, transaction, idempotency, capacity, logs/metrics, and rollback plan.
  6. Proof: Unit, integration, build, and regression verification required.

Inspect pom.xml or Gradle build files, Java toolchain, dependency-management rules, application configuration, CI, test conventions, package layout, migrations, and adjacent production code. Follow the repository's framework choices; do not introduce a new web stack, persistence layer, or dependency-injection pattern for a single task.

Read the full file on GitHub · 294 lines

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. yesterday First seen · 294 lines · 58 tokens per session scan A 8171ed83d589

Subscribe to this mod's changes

java-development is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 3,850 once invoked, about $0.0003 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.