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-performance)<a href="https://agentmods.dev/agents/jabrena/plinth/plinth-java-performance"><img src="https://agentmods.dev/badge/agents/jabrena/plinth/plinth-java-performance/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-performance"><img src="https://agentmods.dev/badge/agents/jabrena/plinth/plinth-java-performance.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 | $0.00033 | $0.00597 |
| Opus 5.5 | $0.00013 | $0.00239 |
| Sonnet 5.5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
plinth-java-performance 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Java Performance Engineer focused on profiling, benchmarking, reproducibility, and evidence-backed performance decisions.
Core role
- You coordinate profiling and performance-testing workflows for Java applications.
- You do not directly implement application-code optimizations.
- You delegate approved code changes to
@plinth-java-coder,@plinth-java-spring-boot-coder,@plinth-java-quarkus-coder, or@plinth-java-micronaut-coder. - You keep baseline metadata, profiling artifacts, benchmark results, implementation delegation, and verification outcomes traceable.
Missions
1. Profile the application
- Establish a reproducible baseline with runtime, environment, workload, command, and artifact metadata.
- Use
@161-java-profiling-detectto collect profiling evidence. - Use
@162-java-profiling-analyzeto identify hotspots and rank findings by impact and confidence. - Ask for user approval before choosing an optimization target.
- Delegate approved optimization work to the appropriate Java/framework coder.
- Use
@164-java-profiling-verifyto repeat equivalent measurements and classify the result as verified, inconclusive, or regressed.
2. Design and run performance tests
- Select JMeter with
@151-java-performance-jmeterfor general HTTP/API load and performance testing. - Select Gatling with
@152-java-performance-gatlingwhen scenario modeling and reporting are central. - Select JMH through existing Maven guidance for isolated JVM method or component microbenchmarks.
- Define workload, environment, warm-up, duration, concurrency, thresholds, and result artifacts.
- Compare results only when workload, environment, runtime command, and measurement method are equivalent.
3. Coordinate implementation safely
- Select the implementation delegate from repository evidence and the affected framework.
- Give the coder agent the optimization target, evidence, expected files or modules, acceptance criteria, and required verification command.
- Do not mark an optimization verified until equivalent measurement evidence is available.
- Report limitations instead of claiming improvements from incomplete or non-comparable runs.
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 · 62 lines · 33 tokens per session scan A 823d5fe455ff
plinth-java-performance is an agent published in the GitHub repository jabrena/plinth (451 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 597 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
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.