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 skills add tmj-90/gaffer --skill java-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/java-conventions)<a href="https://agentmods.dev/skills/tmj-90/gaffer/java-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/java-conventions/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/tmj-90/gaffer/java-conventions"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/java-conventions.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 | $0.00106 | $0.02125 |
| Opus 5.5 | $0.00042 | $0.00850 |
| Sonnet 5.5 | $0.00021 | $0.00425 |
| Haiku 4.5 | $0.00011 | $0.00213 |
Grade A, and why
java-conventions 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 16d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic, modern Java
Java stays correct when data is immutable, resources close themselves, absence is typed and shared state is guarded. For the builder and the reviewer of a Java diff; the repo's config and existing code win over it.
Procedure
- Discover the repo's conventions first. Call
search_lorefor Java conventions. Read the build file (pom.xmlmaven.compiler.release, orbuild.gradle(.kts)toolchain) for the Java version — features below are gated on it — and the wrapper (mvnw/gradlew: always use it). Find the style and analysis tools: Spotless / google-java-format, Checkstyle, Error Prone + NullAway, SpotBugs, PMD, and the nullness annotations in use (JSpecify@NullMarked, JetBrains, jakarta). Note whether the repo uses Lombok (lombok.config) — follow the repo, do not mix styles. Copy a sibling class and its test. - Pin the exact commands from CI (the
run-testsandrun-lintskills). Use the defaults below only when the repo defines none. - Write the change with the idioms below, then walk the concurrency section for every executor, shared field, stream, connection and file you touched.
- Test each acceptance criterion's own behaviour. One JUnit 5 test (or
@ParameterizedTestcase) per AC that fails without your change, plus its error path. If the AC involves shared state or persistence, add a test that runs N concurrent callers (anExecutorServiceplus aCountDownLatchstart gate) and asserts the invariant. Use Testcontainers for real databases where the repo does. - Verify, then stop. Done when: the formatter check and static analysis are clean, the
build's verify/check goal is green with the repo's coverage gate, and every AC has a
test. Record the output with the
record-evidenceskill; the runner submits the work.
Commands
- Maven:
./mvnw -B verify(compile, tests, coverage, checks); one test:./mvnw -Dtest='ClassTest#method' test; format:./mvnw spotless:check. - Gradle:
./gradlew check(orbuild); one test:./gradlew test --tests 'pkg.ClassTest'; format:./gradlew spotlessCheck; coverage:./gradlew jacocoTestReport. - Dependencies: a new or bumped dependency is a blocker, not an edit to the build file
(the
dependency-upgradeskill);./gradlew dependenciesor./mvnw dependency:treeshows what is already on the classpath.
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.
- 16d ago Changed · +41 lines · +17 tokens per session 6700748fb289
- 1mo ago First seen · 86 lines · 89 tokens per session scan A 557947f285d9
java-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,125 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
junit-testing
JUnit 5 testing patterns including annotations, Mockito mocking, Spring Boot test slices, MockMvc, Testcontainers integration, and parameterized tests. Use when the user is writing Java tests, setting up test infrastructure, mocking dependencies, testing Spring controllers, or running integration tests with real…
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
java-affected-tests
Use before opening or updating an OpenMetadata PR that changes Java, a JSON schema, an index mapping, a SQL migration, seed data or a pom — PR CI no longer runs the Java integration tests (they run only in the merge queue) and the JavaUIIT/search-it suites run only nightly, so this selects the unit tests and…