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/goldziher/ai-rulez/java-conventionsnpx skills add Goldziher/ai-rulez --skill java-conventionsgit clone --depth 1 https://github.com/Goldziher/ai-rulezWrote 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/goldziher/ai-rulez/java-conventions)<a href="https://agentmods.dev/skills/goldziher/ai-rulez/java-conventions"><img src="https://agentmods.dev/badge/skills/goldziher/ai-rulez/java-conventions.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 | $0.00050 | $0.00353 |
| Opus 5 | $0.00025 | $0.00177 |
| Sonnet 5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00035 |
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 4d 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.
What it actually says
- Java 17+ LTS, records for immutable data, sealed classes for restricted hierarchies, pattern matching.
- A consistent style guide and auto-formatter (e.g., Google Java Style + google-java-format). Static analysis (e.g., Error Prone + SpotBugs).
- Build: Maven or Gradle with wrapper scripts (
mvnw/gradlew). Commit wrapper files. - Testing: JUnit 5 with
@ParameterizedTest, an assertion library (e.g., AssertJ), a coverage tool (e.g., JaCoCo) at 80%+. - Benchmarking: JMH for microbenchmarks — never use
System.nanoTime()loops. - Error handling: specific exceptions only, never
catch (Exception), use try-with-resources forAutoCloseable. varfor obvious types,Optional<T>for returns (never params/fields),finalfields by default.- Prefer constructor injection over field injection for DI. Immutable collections:
List.of(),Map.of(). - Streams for collection transforms,
instanceofpattern matching, switch expressions. - Security: OWASP
dependency-checkMaven/Gradle plugin for CVE scanning. - Dependencies: commit lock files, use BOM for version alignment, avoid
SNAPSHOTin releases. - Anti-patterns: public fields, mutable static state, raw types, checked exceptions in lambdas.
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.
- 4d ago First seen · 18 lines · 50 tokens per session scan A 7ae8a05a20cf
java-conventions is a skill published in the GitHub repository Goldziher/ai-rulez (140 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 353 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
review
Reviews code changes for concrete bugs with P0-P2 prioritized findings. Uses parallel architectural and implementation reviewers, then validates findings to remove false positives. Use when reviewing a caller-supplied diff, branch, staged changes, file set, or pull request, and use fix mode with caller-supplied…
spec
Writes high-quality product specifications through codebase research, web research, a collaborative requirements interview, and independent review, then gives the user a link to the written spec. Use when planning a feature, defining requirements, revising an existing draft, or creating a spec/PRD. Accepts…
summary
Creates a decision-focused Moss change summary for reviewers who care about the problem, outcomes, trade-offs, and platform implications more than code structure. Use for pull-request summaries, release notes, branch or diff overviews, implementation handoffs, and explanations of what changed and why it matters.…
bjoern-zgr
Use when writing, reviewing, or refactoring .zgr specification files for the Bjoern BDD test generator. Covers syntax, parameter usage for statement reuse, and conventions that reduce the number of methods to implement.
bjoern-gradle-config
Use when configuring the Bjoern Gradle plugin in build.gradle files. Covers all configuration parameters, task setup, and common patterns for code and documentation generation.
agentic-tool-design
Use when designing or reviewing the tools an LLM agent will call — choosing tool boundaries, argument and result shapes, retrieval/search/get decompositions, MCP or goa-ai toolset surfaces — or when an agent misuses existing tools (wrong tool picked, IDs carried between calls, wrong dates computed, confident answers…