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.
git clone --depth 1 https://github.com/kyungseo/ai-workflow-harnessWrote 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/rules/kyungseo/ai-workflow-harness/java-spring)<a href="https://agentmods.dev/rules/kyungseo/ai-workflow-harness/java-spring"><img src="https://agentmods.dev/badge/rules/kyungseo/ai-workflow-harness/java-spring/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/rules/kyungseo/ai-workflow-harness/java-spring"><img src="https://agentmods.dev/badge/rules/kyungseo/ai-workflow-harness/java-spring.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 | $0.00000 | $0.00411 |
| Opus 5.5 | $0.00000 | $0.00164 |
| Sonnet 5.5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
java-spring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Optional Spring Boot Example Rules
These rules are not part of the generic AI Workflow Harness core. They are kept as an optional example/profile surface for projects that adopt the harness with Spring Boot backend code.
MUST:
- Follow the Java and Spring conventions already present in the adopted project.
- Keep package names aligned with the adopted project's namespace.
- Use the adopted project's declared build tool and verification commands.
- Use MyBatis
#{}parameters. Use${}only with whitelist validation and an explanatory comment. - Use Lombok intentionally: prefer
@Getter,@Builder,@RequiredArgsConstructor, and@Slf4j; do not use@Data. - Keep annotation processor order consistent with the adopted project.
- Keep shared exception and response handling in the adopted project's established shared module.
NEVER:
- Add service-specific domain logic to
common-core. - Add default secret values for
JWT_SECRET,DB_PASSWORD, or similar sensitive settings. - Log full tokens, passwords, or
Authorizationheader values.
Comments
MUST:
- Add class-level Javadoc only for: architecture boundaries, security-sensitive logic, complex state. Skip for DTOs, mappers, and standard CRUD controllers.
- Use
// Korean reason — English technical termfor inline comments. Explain WHY, not WHAT. - Let
@Operation,@Schema, and@DisplayNameserve as documentation in their contexts.
NEVER:
- Add comments that repeat what the code already expresses.
- Add file headers (no-header policy; LICENSE file covers the project).
Full reference: docs/HARNESS-MAINTAINER-GUIDE.md
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.
- 1mo ago First seen · 44 lines · 0 tokens per session scan A 4013ff651b4c
java-spring is a cursor rule published in the GitHub repository kyungseo/ai-workflow-harness (14 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 411 tokens. 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 cursor rules, from other repositories
010-python-tooling
Python tooling and dependency conventions for plugin-eval and tools/.
java-general-purpose-cursorrules-prompt-file
Cursor rules for Java General Purpose.
springboot-jpa-best-practices
A set of Chinese-language rules for structuring Java Spring Boot applications that use JPA, a library for database access.
entity-class-conventions
A set of rules for Java classes that represent database records, called entities. It defines required annotations, automatic ID creation, lazy relationship loading, and field validation.
general-java-development-practices
A set of rules for writing Java code, including guidance on keeping designs focused, avoiding repetition, and following OWASP security practices. OWASP is a group that publishes guidance for building safer software.
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.