Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cosmix/loomnpx agentmods add skills/cosmix/loom/loom-javaWrote 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/cosmix/loom/loom-java)<a href="https://agentmods.dev/skills/cosmix/loom/loom-java"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-java/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/skills/cosmix/loom/loom-java"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-java.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 | $0.00014 | $0.06971 |
| Opus 5.5 | $0.00006 | $0.02788 |
| Sonnet 5.5 | $0.00003 | $0.01394 |
| Haiku 4.5 | $0.00001 | $0.00697 |
Grade A, and why
loom-java scanned grade A with 1 finding 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 21d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
.map(url -> executor.submit(() -> fetch(url))) // one virtual thread per blocking call How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Language Expertise
Overview
Idiomatic, production-grade Java 21+ (25 is the current LTS): records, sealed hierarchies, pattern matching, streams, virtual threads, the Maven and Gradle builds, JUnit 5 and Spring Boot. Assumes the reader knows the language. The content is decision rules and the traps that survive review: == on boxed values, Collectors.toMap on a duplicate key, @Transactional on a self-call, a pinned virtual thread, a test task that runs zero JUnit 5 tests and reports success.
Tooling
Use the wrapper the repository ships (./gradlew, ./mvnw); it pins the build tool version. Keep the existing build tool: a Maven-to-Gradle migration is a separate, requested change.
| Task | Gradle | Maven |
|---|---|---|
| Full gate | ./gradlew check |
./mvnw -q verify |
| Compile main and tests | ./gradlew testClasses |
./mvnw -q test-compile |
| Unit tests | ./gradlew test |
./mvnw -q test |
| One test | ./gradlew test --tests 'com.acme.FooTest.bar' |
./mvnw test -Dtest='FooTest#bar' |
| Dependency tree | ./gradlew dependencies --configuration runtimeClasspath |
./mvnw dependency:tree |
| Why is X on the classpath | ./gradlew dependencyInsight --dependency jackson-databind |
./mvnw dependency:tree -Dincludes=com.fasterxml.jackson.core |
| Format | ./gradlew spotlessApply |
./mvnw spotless:apply |
- Gradle:
checkrunstestplus every verification task a plugin attaches (Spotless'sspotlessCheck, Checkstyle, SpotBugs); Error Prone runs insidecompileJava.buildischeckplusassemble. Atesttask whose inputs have not changed is skipped asUP-TO-DATE;--rerun(Gradle 7.6+) forces it. - Maven: Surefire runs unit tests in the
testphase (default includes**/Test*.java,**/*Test.java,**/*Tests.java,**/*TestCase.java); Failsafe runs*IT.javainintegration-test/verify. Pinmaven-surefire-plugin3.x in<pluginManagement>: older Maven super-POMs bind Surefire 2.12.4, which runs no JUnit 5 tests and reports success. - Versions: Gradle keeps them in the version catalog (
gradle/libs.versions.toml) and imports BOMs withplatform(...); Maven imports BOMs in<dependencyManagement>with<scope>import</scope>. Conflict resolution differs: Gradle picks the highest requested version, Maven picks the nearest declaration in the tree, which can silently downgrade a transitive dependency.maven-enforcer-plugin'sdependencyConvergencerule turns that into a build error. - Static analysis:
javac -Xlint:all -Werror; Error Prone (javac plugin, compile-time bug patterns); NullAway (an Error Prone check) with JSpecify@NullMarked/@Nullable; SpotBugs on bytecode; Checkstyle or PMD for style rules. Format with Spotless running google-java-format or palantir-java-format.
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.
- 21d ago First seen · 396 lines · 14 tokens per session scan A aea400ccb080
loom-java is a skill published in the GitHub repository cosmix/loom (62 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 6,971 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
authoring-java-sdk-tasks
Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…
configuring-airflow-language-sdks
Configures Airflow to run language SDK tasks (Java, Go, and future native SDKs) — register a coordinator, map a queue to it, ensure the runtime/artifact on workers, and tune coordinator options. Use when the user wants Airflow to route a queue to a native-language coordinator, asks about the [sdk]…
aws-sdk-java-v2-bedrock
Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration. Use when asking about Bedrock integration, Java SDK for AI models, AWS generative…
aws-lambda-java-integration
Provides AWS Lambda integration patterns for Java with cold start optimization. Use when deploying Java functions to AWS Lambda, choosing between Micronaut and Raw Java approaches, optimizing cold starts below 1 second, configuring API Gateway or ALB integration, or implementing serverless Java applications. Triggers…
langchain4j-ai-services-patterns
Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based patterns, annotations, memory management, and tools integration. Use when creating AI-powered Java…
unit-test-parameterized
Provides parameterized testing patterns with JUnit 5, generates data-driven unit tests using @ParameterizedTest, @ValueSource, @CsvSource, @MethodSource. Creates tests that run the same logic with multiple input values. Use when writing data-driven Java tests, multiple test cases from single method, or boundary value…