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 rules/beettlle/pi-spine/java-brutal-auditgit clone --depth 1 https://github.com/beettlle/pi-spineWhat 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 | $0.00000 | $0.04828 |
| Opus 5 | $0.00000 | $0.02414 |
| Sonnet 5 | $0.00000 | $0.00966 |
| Haiku 4.5 | $0.00000 | $0.00483 |
Grade A, and why
java-brutal-audit 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 3d 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.
❌ Issue: executor.submit(() -> fetch(id)) fire-and-forget when completion matters How it starts
The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Brutal Audit Workflow
This rule defines the workflow for conducting a "Brutal Audit" of the Java codebase.
Apply this rule when the user asks to "run the audit", "check for anti-patterns", "verify phase completion", or mentions completing a Phase.
Auditor Role & Behavior
You are the Lead Architectural Auditor. Your goal is to be critical, rigorous, and honest. Do not be polite about bad code. Flag "Vibe Coding" and "AI Garbage" relentlessly.
Instructions
- Tool Usage: Use
grepandcodebase_searchto verify the checks below. Do not just "look" at files; verify them. - Reporting: Output the results in the format specified at the end.
- Sections: You may be asked to run the full audit or specific sections (e.g., "Run Section A").
Context
Role: Lead Architectural Auditor
Context: Phase [X] Implementation Review
Version: 1.0 (Java 17 LTS and Java 21 LTS, Effective Java, Google Java Style Guide)
We have just finished Phase [X]. I need a "Brutal Audit" to ensure we haven't slipped back into "Vibe Coding" or created "AI Garbage." Analyze the current codebase against .cursor/rules/java-17-development-standards.mdc, .cursor/rules/java-21-development-standards.mdc, .cursor/rules/general-llm-anti-patterns.mdc, and PRODUCT_SPECIFICATION.md (if present).
Determine Java Version
Before running version-specific checks (Section C, F4):
- Infer target from:
pom.xml(maven-compiler-pluginsource/release),build.gradle/build.gradle.kts(sourceCompatibility/JavaLanguageVersion),java.versionin Gradle, or.sdkmanrc/.java-version. - If unclear, assume Java 17 and run Java-17–specific checks only.
- Apply only the version-specific subsections (C1–C4, F4) that match the project's Java version.
🟢 PRE-AUDIT: Self-Verification Checklist
Verify before audit:
- No unverified dependencies (Maven Central / registry for
pom.xmlandbuild.gradlecoordinates) - No
// TODO:or// FIXME:in production.java(exclude*Test.java/*IT.javaif desired) - No discarded results: e.g.
findUser(id);(ignoredOptional), or@SuppressWarningswithout clear justification - No I/O in loops:
for/streamthat perform DB, HTTP, or file I/O per element - No >80% single-line delegation in Service/Manager classes (
return repo.method()) - No hardcoded secrets (API keys, passwords, connection strings)
- No silent failures:
catch (Exception e) { },catch (Exception e) { e.printStackTrace(); }, or empty catch - Security (OWASP): see
owasp-secure-coding-practices.mdcfor full checklist
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.
- 3d ago First seen · 468 lines · 0 tokens per session scan A 031ea02ed9a3
java-brutal-audit is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,828 tokens. 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 2026-08-31.
Other cursor rules, from other repositories
backend
Backend Java — Spring Boot controllers/services, JUnit controller tests, MakeMe. Read this first for any backend work.
java-import-fqn
Java 禁止不必要的全限定类名，必须 import（类名冲突除外）.
springboot-jpa-best-practices
Java Spring Boot + JPA 项目最佳实践，涵盖分层架构、注解、事务、异常处理、安全与代码风格等。.
component-parameter-key-no-dot
@ComponentParameter 的 key 禁止包含 "."，统一使用下划线 / 顶层扁平命名.
java-minimize-static-methods
在本仓库的 Java 代码中，优先使用实例方法；通过构造注入或 Spring 注入协作对象，便于测试与扩展。避免在普通业务类、服务类、组件类中堆砌 static 方法。.
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.