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/zyx379/zoehis_workflowWrote 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/zyx379/zoehis_workflow/zoehis-code-review)<a href="https://agentmods.dev/rules/zyx379/zoehis_workflow/zoehis-code-review"><img src="https://agentmods.dev/badge/rules/zyx379/zoehis_workflow/zoehis-code-review.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 5.1 | $0.02117 | $0.02117 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00423 | $0.00423 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
zoehis-code-review 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 7d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZOEHIS AI 局部审查(Step 8)
改动完成后、人工审查前,对 本次 diff 做局部审查并输出结论。详见 docs/workflow.md Step 8。
本规则将「Java/Spring Boot 企业级代码生成约束」转换为 审查视角 的检查清单:生成阶段该遵守的,审查阶段逐条核对是否已遵守;命中即标记 违规,给出改法,结论置为 需修改,不得放行进入 Step 9。
1. 规范与数据流
- 命名、代码风格(
dev/rules/zoehis-*.mdc) - 池表 / 主细表 / 预交金 / 流水完整性(同 Step 7,针对改动点)
2. Java/Spring Boot 企业级规范(必查)
对新增/修改的 Java/Spring 代码逐项核查;命中任一项即标记 违规 并给出改法,不得进入 Step 9。
2.1 异常处理(强制)
- 禁止空
catch:catch (Exception e) {}→ 必须记录日志并向上抛出 - 禁止吞 cause:禁止
throw new RuntimeException("失败")丢原异常 → 必须throw new RuntimeException("失败", e) - 必须保留原始 cause、记录完整异常日志(含堆栈
log.error("执行失败", e)) - 禁止静默吞异常(catch 后不处理也不抛出,return 掩盖错误)
2.2 事务规范(强制)
-
@Transactional仅标注 public 方法;禁止 private/protected 方法加事务(不生效) - 必须声明
rollbackFor = Exception.class,禁止依赖默认回滚(默认仅回滚 RuntimeException) - 禁止同类内部 self-invoke 调用本类事务方法(事务失效):改用 AOP 代理调用 / 抽取独立 Service / 注入自身代理
- 多表写、池表删增未同事务 → 标记风险并提示
2.3 afterCommit(最高优先级)
- 若使用
TransactionSynchronizationManager/afterCommit()/TransactionSynchronizationAdapter - 其中任意 DB 写(insert/update/delete/save/saveBatch/Mapper/Repository)必须 新开物理事务,满足其一:
- ①
@Transactional(propagation = Propagation.REQUIRES_NEW) - ②
TransactionTemplate - ③ AOP 代理调用且代理方法声明
REQUIRES_NEW
- ①
- 禁止 afterCommit 中直接写库而未开启新事务(主事务已提交,内部写不受控 / 事务失效)
2.4 金额计算(强制)
- 金额字段、金额运算必须使用
BigDecimal,禁止double/Double/float/Float - 禁止金额
==比较,必须用compareTo()/equals() - 禁止浮点字面量参与金额运算(如
1.1 * qty→new BigDecimal("1.1").multiply(...))
2.5 线程安全
- 禁止共享
SimpleDateFormat(静态共享变量)→ 改用DateTimeFormatter或局部变量/ThreadLocal - 禁止共享可变
HashMap/ArrayList等非线程安全容器(线程间复用导致数据错乱) - 共享对象必须保证线程安全(或改为方法局部变量)
2.6 异步任务
- 出现
@Async的类中,项目须存在@EnableAsync与ThreadPoolTaskExecutor配置;缺一则@Async不生效 → 补全配置或移除注解 - 异步方法内异常需有明确兜底,避免静默丢失
2.7 依赖注入
- 统一
@RequiredArgsConstructor+ 构造器注入;禁止@Autowired字段注入 - 禁止在字段上直接
@Autowired(破坏不可变性与可测试性)
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.
- 7d ago First seen · 143 lines · 2,117 tokens per session scan A 9f538faa9350
zoehis-code-review is a cursor rule published in the GitHub repository zyx379/zoehis_workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,117 tokens to every session, about $0.0106 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 2026-08-31.
Other cursor rules, from other repositories
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.