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 cocoCzl/coco-skills --skill java-coding-standardsgit clone --depth 1 https://github.com/cocoCzl/coco-skillsWrote 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/cococzl/coco-skills/java-coding-standards)<a href="https://agentmods.dev/skills/cococzl/coco-skills/java-coding-standards"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/java-coding-standards/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/cococzl/coco-skills/java-coding-standards"><img src="https://agentmods.dev/badge/skills/cococzl/coco-skills/java-coding-standards.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 | $0.00160 | $0.01802 |
| Opus 5.5 | $0.00064 | $0.00721 |
| Sonnet 5.5 | $0.00032 | $0.00360 |
| Haiku 4.5 | $0.00016 | $0.00180 |
Grade A, and why
java-coding-standards 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 15d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java 编码规范
用于实际代码实现、局部格式调整及代码审查,依据目标项目 Java 版本选择规则、语法和 API,不预设固定版本基线。示例的最低版本仅限定示例 API,不代表所有 JDK 已验证;验证限制见 README。仅分析关系生成 ERD 由 java-code-to-erd 负责,仅提取履历由简历 Skill 负责;任务同时要求改 Java 时,仅对改动部分应用本 Skill。纯解释不启动检查、构建或重构流程。
这是适用于各类 Java 编码环境的通用规范 Skill。在 Codex CLI、VS Code、IDEA 或其他环境应用时,均按下述优先级执行适用的文字规则;不依赖安装 IDEA、读取/导入 XML 或调用 IDEA 格式化器。
优先级
遵循运行环境指令层级。在不冲突时,用户当前明确要求、目标目录项目明确规范优先;项目明确规则只覆盖对应的 Skill 默认条目,其他适用规则继续执行。例如项目缩进覆盖默认缩进,不取消异常处理或资源释放要求。生效的格式化、静态检查、构建配置决定执行方式;检查未启用某条规则不代表无需遵守。有格式配置也要应用其余适用条目。相邻代码只是补充证据,不复制已有错误。
配置不一致先查模块、目录、profile、source set 和 CI 生效范围;只有仍无法解决且影响任务的冲突才询问。不要改全局 IDE 设置、擅加插件或升级 Java。
下文【强制】【推荐】【参考】是手册原级别;推荐项可说明权衡,参考项按场景选择,不升级为硬门禁。【融合决策】是本 Skill 对冲突或 API 条件的执行结论,不冒充手册原文。
编写前
- 确认任务是实现、修复、重构、格式化还是只读审查,圈定文件及必要调用方。
- 读取目标路径适用的项目指令,按需看父/模块 POM、Gradle 构建与 toolchain、编译 release/source/target、已有检查配置和 CI 命令。运行 JDK 不等于编译目标;不要无差别全仓扫描。版本不明先沿用现有可确认语法,不擅用新 API;会影响实现时再澄清。
- 仅加载下面与任务相关的资料;普通 DTO 默认只需本入口和命名与结构,涉及金额、数值或日期字段及其计算、比较、转换时再读相应资料;缺省排版要处理细节时才读格式资料。不要读完整手册或全部 references。
编写中
- 最小必要修改;不顺带全仓格式化、重命名或重构。审查请求默认只报告有位置、影响和建议的问题。
- 缺省排版:4 空格缩进、续行 +4、100 列边界、非空控制块加大括号;Java 类头后 1 空行。细节按 格式文字规则 执行,不必读取 XML;不要按 GoogleStyle 名称套标准 Google Java Style。
- 【强制】类 UpperCamelCase(DTO 等缩写例外)、成员/方法 lowerCamelCase、常量 UPPER_SNAKE_CASE;覆盖方法加
@Override(一(一)4–6、一(四)2)。 - 【强制】包装整数的值比较用空值安全的 equals;拆箱前确认非 null,不靠捕获 NPE 做条件判断(一(四)6–7、二(二)1)。
- 【强制】异常不能吞掉、
finally不 return;拥有的资源在异常路径也要释放(二(二)4、6–7)。 - 【强制】外部输入校验与权限校验不能缺失;SQL 值参数绑定,不能拼接用户输入(四 1、3–4)。不要将内部已验证参数机械地每层重复校验(一(八)13–14【参考】)。
- 保持 API、序列化和数据语义兼容;规则例外要有项目要求或实际 API 条件依据。不要为“通过”删测试、关闭规则或压制告警。
完成后
- 自查 diff、新增/修改代码及必要关联位置,确认行为、边界、异常路径和改动范围。
- 复用项目现有格式化、静态检查、编译与相关测试。先查任务命令是否会全仓写入;用已有检查模式/文件范围,不能限定时人工检查本次 diff。不把 google-java-format 当作此 IDEA XML 的等价实现。
- 纯格式调整核对 diff 与可用格式检查即可,遵守项目必需检查;行为修改选择相关编译/测试,缺回归保障的核心行为补有价值测试。无新失败、改动或风险,不反复全量构建;不为简单 DTO/getter 机械生成测试。
- 缺工具时仍按适用的文字规范编写并按范围人工自查,说明哪些未自动验证;不擅自安装或修改构建。简要交代改动、执行过的检查及限制,不要求 JSON、doctor、route 或运行报告。
按需资料
| 任务涉及 | 读取 |
|---|---|
| 默认排版细节、Java 导入声明或工具差异 | formatting.md;仅需配置 IDEA 时选用 IDEA XML 资产 |
| 新类/DTO、命名、接口、注释、序列化 | naming-and-structure.md |
| 金额、数值、日期字段及其比较、计算、转换 | numbers-and-dates.md |
| 集合、泛型、流、比较器 | collections.md |
| 异常处理、日志、错误边界 | exceptions-and-logging.md |
| 共享状态、锁、线程池、ThreadLocal、异步 | concurrency.md |
| 文件/连接/流生命周期、外部输入、权限、远程调用 | resources-and-security.md |
| JDBC、ORM、SQL、事务 | database.md,拥有资源时加资源资料,修改异常处理时加异常资料 |
| 编写/修改测试,或行为变化需设计回归 | testing.md |
| 新语法/API、编译/运行 JDK 不同、版本兼容判断 | java-versions.md |
| 来源追溯、规则冲突、record/switch/虚拟线程等版本条件 | sources-and-decisions.md,只看相关条目 |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 313 B
- assets/java-code-style.xml 4.2 KB
- README.md 4.1 KB
- references/collections.md 2.5 KB
- references/concurrency.md 2.3 KB
- references/database.md 2.8 KB
- references/exceptions-and-logging.md 2.9 KB
- references/formatting.md 4.1 KB
- references/java-versions.md 4.0 KB
- references/naming-and-structure.md 2.9 KB
- references/numbers-and-dates.md 1.8 KB
- references/resources-and-security.md 1.8 KB
- references/sources-and-decisions.md 7.0 KB
- references/testing.md 1.8 KB
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.
- 15d ago First seen · 60 lines · 160 tokens per session scan A 1fa1a31dd022
java-coding-standards is a skill published in the GitHub repository cocoCzl/coco-skills (5 stars, last pushed 16d ago), licensed MIT. It adds 160 tokens to every session and 1,802 once invoked, about $0.0006 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 2026-10-24.
java-coding-standards compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| java-coding-standardscocoCzl/coco-skills | Skill | 5 | 16d ago | MIT | A | 160 | Codex |
| solid-principlesdecebals/claude-code-java | Skill | 770 | 9d ago | MIT | A | 73 | Claude Code, Codex |
| concurrency-reviewdecebals/claude-code-java | Skill | 770 | 9d ago | MIT | A | 58 | Claude Code, Codex |
| java-code-reviewdecebals/claude-code-java | Skill | 770 | 9d ago | MIT | A | 45 | Claude Code, Codex |
| 814-regulations-iso-25010jabrena/plinth | Skill | 461 | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| 121-java-object-oriented-designjabrena/plinth | Skill | 461 | yesterday | Apache-2.0 | A | 107 | Claude Code, Codex |
| 053-design-simple-rulesjabrena/plinth | Skill | 461 | yesterday | Apache-2.0 | A | 86 | Claude Code, Codex |