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/eclipse-rdf4j/rdf4j/high-performance-javanpx skills add eclipse-rdf4j/rdf4j --skill high-performance-javagit clone --depth 1 https://github.com/eclipse-rdf4j/rdf4jWrote 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/skills/eclipse-rdf4j/rdf4j/high-performance-java)<a href="https://agentmods.dev/skills/eclipse-rdf4j/rdf4j/high-performance-java"><img src="https://agentmods.dev/badge/skills/eclipse-rdf4j/rdf4j/high-performance-java.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.02392 |
| Opus 5 | $0.00070 | $0.01196 |
| Sonnet 5 | $0.00028 | $0.00478 |
| Haiku 4.5 | $0.00014 | $0.00239 |
Grade A, and why
high-performance-java 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
High-Performance Java
Use this skill for Java hot paths, algorithm-heavy Java, and JVM-side runtime specialization. Default bias: asymptotic win first, then the right execution model, then fewer allocations, fewer copies, less polymorphism, narrower code shape, stronger evidence.
HotSpot-only v1. Baseline assumptions:
- repo baseline: JDK 21
- current local runtime may be newer
- low-level claims stay provisional until benchmark + JIT evidence agree
- algorithm/data-structure claims stay provisional until they match the actual workload constraints
- runtime codegen claims stay provisional until cold-start cost, warm steady-state behavior, and fallback behavior are all understood
Core loop
- Identify the workload shape and constraints.
- Pick the algorithm and data structure that change the slope.
- Decide whether the workload should stay interpreted, become vectorized/batched, or justify runtime specialization/code generation.
- Find the hot loop, hot call chain, or hot operator pipeline.
- Write the narrow fast path first.
- Push generic abstraction, materialization, and dispatch out of the loop.
- Benchmark before claiming improvement.
- Inspect HotSpot decisions before claiming JVM-level reasons.
Default coding bias
- Prefer an algorithmic win over a micro win.
- Prefer data structures that fit the operation mix, memory budget, and key domain.
- Prefer the right execution model over reflexively adding code generation.
- Prefer primitive-friendly layouts before boxed object graphs.
- Prefer zero-copy over copy-transform-copy.
- Prefer reuse over per-item allocation.
- Prefer lazy traversal over full materialization.
- Prefer primitives, flat arrays, and tight counted loops in hot paths.
- Prefer monomorphic calls that inline away.
- Prefer specialized lambda/adaptor code for the active workload.
- Prefer one fast path plus one cold fallback over a single generalized hot path.
- Prefer Janino only when generated Java can stay simple, code size can stay bounded, and compile cost can be amortized.
What ships with it
8 files 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.
- agents/openai.yaml 376 B
- references/advanced-coding-techniques.md 6.0 KB
- references/algorithms-data-structures.md 7.0 KB
- references/codegen-and-janino.md 9.4 KB
- references/coding-rules.md 3.5 KB
- references/evidence-workflow.md 2.7 KB
- references/high-performance-java-libraries.md 7.3 KB
- references/jdk-21-26-notes.md 1.4 KB
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 · 195 lines · 140 tokens per session scan A 56bdf6776673
high-performance-java is a skill published in the GitHub repository eclipse-rdf4j/rdf4j (412 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 140 tokens to every session and 2,392 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
mcp-sparql
Exposes SPARQL query capabilities to LLMs via the Model Context Protocol. Supports SELECT, ASK, CONSTRUCT, and DESCRIBE queries against any SPARQL endpoint.
knowledge-graph-sparql
Knowledge graph construction, SPARQL querying, and entity linking for library and research data management using RDF and Wikidata.
azure-communication-common-java
Azure Communication Services common utilities for Java. Use when working with CommunicationTokenCredential, user identifiers, token refresh, or shared authentication across ACS services.
azure-security-keyvault-secrets-java
Azure Key Vault Secrets Java SDK for secret management. Use when storing, retrieving, or managing passwords, API keys, connection strings, or other sensitive configuration data.
azure-ai-anomalydetector-java
Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate/multivariate anomaly detection, time-series analysis, or AI-powered monitoring.