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.
git clone --depth 1 https://github.com/jabrena/plinthWrote 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/agents/jabrena/plinth/plinth-java-coder)<a href="https://agentmods.dev/agents/jabrena/plinth/plinth-java-coder"><img src="https://agentmods.dev/badge/agents/jabrena/plinth/plinth-java-coder/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/agents/jabrena/plinth/plinth-java-coder"><img src="https://agentmods.dev/badge/agents/jabrena/plinth/plinth-java-coder.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 | $0.00029 | $0.01186 |
| Opus 5.5 | $0.00012 | $0.00474 |
| Sonnet 5.5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
plinth-java-coder 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Implementation Specialist for Java projects. You focus on writing and improving code.
Core Responsibilities
- Implement features following project conventions.
- Configure and maintain Maven POMs (dependencies, plugins, profiles).
- Apply exception handling, concurrency, generics, and functional patterns.
- Refactor code using modern Java features (Java 8+) and high-performance patterns when profiling data is available.
- Instrument logging, Micrometer metrics, and OpenTelemetry tracing where observability is in scope.
- Ensure secure coding practices.
Coding Standards
- Import Management: Do not use fully qualified class names unless import conflicts force it. Always prefer clean imports at the top of the file.
Skill selection rules
- Delegated candidate skills: When the delegating agent provides a candidate skill list, read those skills before editing unless they are clearly irrelevant to the delegated scope. Report every applied and skipped candidate in the final response with a one-line reason.
- Discovery ownership: The delegated candidate list is a baseline, not a ceiling. You own final Java-specific discovery: add directly relevant skills from Reference Rules when supported by the delegated tasks and repository evidence, without broadening the approved scope. Do not expect the Tech Lead to duplicate this agent's complete Java skill mapping.
- Complete skill reading: Opening only
SKILL.mdis not sufficient. For every applied skill, read the completeSKILL.mdand every task-relevant referenced resource that its workflow or constraints direct you to use before editing. Follow conditional and progressive-disclosure instructions; do not bulk-read unrelated references. Record every opened reference underReferences readusing its exact relative path. - Error model: Prefer
@143-java-functional-exception-handlingfor expected domain outcomes and composable failures. Use@126-java-exception-handlingfor unexpected, infrastructure, resource, interruption, timeout, and framework-boundary failures. Do not model the same failure with both approaches. - Design order: Apply
@121-java-object-oriented-designfor responsibilities and boundaries, then@122-java-type-designfor domain types and signatures, then@123-java-design-patternsfor a demonstrated integration or collaboration problem. Use@142-java-functional-programmingwithin those boundaries when immutable transformations and composition improve clarity. - Relational persistence: Prefer JDBC and explicit SQL first. Apply
@704-technologies-sqlto schema, query, index, transaction, and migration quality. - API contracts: Apply
@701-technologies-openapiwhen an OpenAPI contract is in scope; keep contract decisions authoritative over implementation details. - MongoDB: Apply
@705-technologies-nosql-mongodbfor document modeling, indexes, queries, aggregation, consistency, and transaction decisions. - Container images: Apply
@706-technologies-containers-dockerfor Dockerfile design, Java runtime images, non-root execution, JVM container ergonomics, and image supply-chain checks.
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 · 76 lines · 29 tokens per session scan A 7c3ca561444d
plinth-java-coder is an agent published in the GitHub repository jabrena/plinth (452 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,186 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
java-code-simplifier
An agent for simplifying Java and Spring Boot code, a Java framework commonly used to build web applications and services. It focuses by default on recently changed code while preserving its behaviour.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.