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 flanliulf/SpecLite --skill speclite-brownfield-java-springboot-backend-tech-stack-diggergit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-brownfield-java-springboot-backend-tech-stack-digger)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-brownfield-java-springboot-backend-tech-stack-digger"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-brownfield-java-springboot-backend-tech-stack-digger/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/flanliulf/speclite/speclite-brownfield-java-springboot-backend-tech-stack-digger"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-brownfield-java-springboot-backend-tech-stack-digger.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 | $0.00145 | $0.01246 |
| Opus 5 | $0.00072 | $0.00623 |
| Sonnet 5 | $0.00029 | $0.00249 |
| Haiku 4.5 | $0.00015 | $0.00125 |
Grade A, and why
speclite-brownfield-java-springboot-backend-tech-stack-digger 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 6d 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
[Overview(技能说明)]
Speclite Brownfield Java SpringBoot Backend Tech Stack Digger 是 1-analysis 阶段的 Java / Spring Boot 后端技术栈挖掘工作流。它继承 speclite-brownfield-backend-tech-stack-digger 的通用报告契约,并专门处理 Maven / Gradle、BOM、Spring Boot、Spring Cloud、Servlet 容器、JDBC、ORM、调度、缓存、安全认证等 Java 生态事实。
[Core Capabilities(核心能力)]
- Java 模块发现:识别 Maven / Gradle root、module、parent POM、BOM、bootstrap module、service module 和 packaging 方式。
- 依赖版本解析:优先使用 Maven effective-POM、dependency tree、Gradle dependencies、lockfile 和 dependencyManagement 解析实际版本。
- Spring 生态识别:提取 Spring Boot、Spring Framework、Spring Cloud、Spring Cloud Alibaba、Spring Security、Actuator、OpenFeign、Gateway 等版本与用途。
- 运行时与容器识别:确认 Java / JDK 版本、compiler target、toolchain、Docker runtime image、embedded Tomcat / Jetty / Undertow 或外置容器。
- 数据访问分析:识别 JDBC driver、datasource、connection pool、MyBatis、MyBatis-Plus、JPA / Hibernate、Flyway / Liquibase 和 DDL 事实。
- 中间件与工程能力分类:识别 MQ、Redis client、local cache、scheduler、object storage、HTTP client、serialization、mapping、API docs、test stack 和 observability。
- 证据化 Markdown 输出:按 assets/java-springboot-tech-stack-report-template.md 生成编号清单、证据摘要、未确认项和核验命令。
[Workflow(执行流程)]
本 Skill 使用 Java / Spring Boot 专属顺序分析工作流。详细版本解析、类别矩阵和命令策略见 references/java-springboot-tech-stack-workflow.md。
1. 解析用户输入,确认 `{project-root}`、`{output-dir}` 和 `{report-name}`。若 `{output-dir}` 缺失,必须先询问。
2. 读取通用报告契约:输出必须兼容 `speclite-brownfield-backend-tech-stack-digger` 的章节结构和证据原则。
3. 扫描 Java 构建入口:根 `pom.xml` / `build.gradle`、module POM、parent POM、BOM、`settings.gradle`、`gradle.lockfile`、`maven-wrapper.properties`、`gradle-wrapper.properties`。
4. 可执行解析优先:Maven 项目运行 `help:effective-pom` 和 `dependency:tree`;Gradle 项目运行 `dependencies`。失败时记录原因并退回静态文件解析。
5. 读取 runtime config 与源码入口,补充 Spring Boot、Servlet container、datasource、Redis、MQ、scheduler、storage、security、API docs、observability 和 test facts。
6. 合并事实并标注来源。client 版本不得推断 server 版本;外部服务端版本必须来自 deploy evidence。
7. 写入 `{output-dir}/{report-name}`,默认 `java-springboot-backend-tech-stack.md`;最终回复给出路径、关键版本和未确认项。
[Notes(注意事项)]
- 本 Skill 只分析 Java / Spring Boot 后端技术栈;Node.js、Python、Go、.NET 等生态应使用各自专属 Skill 或通用后端契约。
- 依赖版本来自 parent POM、BOM、internal framework、dependencyManagement 或 Gradle platform 时,必须写清楚解析来源。
- Spring Boot 版本不等于 spring-boot-maven-plugin 版本;优先使用 spring-boot-dependencies.version 或 resolved dependency facts。
- Tomcat / Jetty / Undertow 版本优先来自 effective dependency,不得只凭 Spring Boot 大版本推断具体补丁版本。
- PostgreSQL Server、Redis Server、RocketMQ Server、MinIO Server 等外部服务端版本不能由 Java client 版本反推。
- 生成报告必须包含 Generated By(生成来源) 标注:speclite-brownfield-java-springboot-backend-tech-stack-digger。
[Generation Metadata(生成信息)] 本 Skill 由 skills-creator 从通用后端技术栈报告契约中拆分 Java / Spring Boot 生态规则生成。后续修改必须同步更新 SKILL.md、SKILL.en.md、CHANGELOG.md,并同步 forge/ 与 SpecLite assets 源目录。
What ships with it
6 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.
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.
- 6d ago First seen · 50 lines · 145 tokens per session scan A 13d5492b9bf7
speclite-brownfield-java-springboot-backend-tech-stack-digger is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 145 tokens to every session and 1,246 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
API Design Checklist
Naming, status-code, error-shape, and versioning conventions for keeping an API internally consistent as it grows.
Backend Test Patterns
Guidance for covering the failure and edge paths of a backend change — bad input, concurrent writes, partial failure — not just the happy path.
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
Layered Architecture
Controller → service → repository layering, DTO boundaries, @Transactional placement, and exception hierarchy.
Contract-First Development
How to define, document, and maintain the shared contract between frontend and backend.
Full-Stack Error Handling
Error propagation patterns — backend error shape to API response to frontend fetch wrapper to UI state.