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 jiushiwon/wg-skills --skill springboot-agent-module-skillgit clone --depth 1 https://github.com/jiushiwon/wg-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/jiushiwon/wg-skills/springboot-agent-module-skill)<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/springboot-agent-module-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/springboot-agent-module-skill/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/jiushiwon/wg-skills/springboot-agent-module-skill"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/springboot-agent-module-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 108 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 111 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Data Exfiltration · line 443 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00150 | $0.08880 |
| Opus 5 | $0.00075 | $0.04440 |
| Sonnet 5 | $0.00030 | $0.01776 |
| Haiku 4.5 | $0.00015 | $0.00888 |
Grade A, and why
springboot-agent-module-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 708 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spring Boot Agent Module Skill
为 Spring Boot 项目叠加一套 AI Agent 能力，基于 Spring AI 1.0 框架实现。
版本策略：不硬编码 JDK/Spring Boot 版本，遵循
springboot-init-skill骨架的版本获取策略。 骨架验证基线：Spring Boot 3.3.5 + jjwt 0.12.6 + springdoc 2.6.0（见skeleton.md第82行）。 本模块要求 JDK 17+（Spring AI 1.0 最低要求）。
定位
- 目标：在已有
springboot-init-skill骨架 +springboot-auth-module-skill鉴权模块上，添加 AI Agent 对话能力。 - 核心：Spring AI ChatClient + Function Calling + Tool 扩展 + 上下文记忆 + 安全防护。
- 输出：Agent 核心、Tool 定义、Controller、数据库模型、接口契约、测试用例、部署指南。
骨架依赖
本模块依赖
springboot-init-skill骨架 +springboot-auth-module-skill鉴权模块。
使用前必须满足：
- ✅ 已安装
springboot-init-skill（项目骨架） - ✅ 已安装
springboot-auth-module-skill（用户鉴权） - ✅ 骨架包含：JWT（jjwt 0.12.x）、
ApiResponse统一响应、@RestControllerAdvice异常处理、@CurrentUser注解、{prefix}表前缀、MySQL、Flyway
对接规范（必须遵循）：
- ✅ 使用骨架的
.env+application.yml（${ENV_VAR:default}）配置系统 - ✅ 使用骨架的
ApiResponse统一响应（ResponseBodyAdvice自动包装） - ✅ 使用骨架的
GlobalExceptionHandler异常处理（BusinessException/ 校验异常 / 兜底异常） - ✅ 使用骨架的
@CurrentUser Long userId获取当前用户（CurrentUserArgumentResolver） - ✅ 使用骨架的
{prefix}表前缀（默认wg） - ✅ 使用骨架的
SecurityConfig安全配置（不重复定义安全头） - ✅ 使用骨架的 Flyway 迁移管理（
src/main/resources/db/migration/） - ✅ 使用骨架的 Spring Data JPA（
spring-boot-starter-data-jpa）作为 ORM - ✅ 使用骨架的 SseEmitter（
spring-boot-starter-web）实现 SSE，不引入 WebFlux - ✅ 使用骨架的
restart.sh部署脚本 - ✅ 使用骨架的
springdoc-openapi 2Swagger 文档（/swagger-ui.html） - ✅ Agent 模块注册到 Spring 容器，通过
@Autowired注入
用户问题（最多 3 个）
1. 用什么模型？（默认 OpenAI gpt-4o-mini，可选 Claude/DeepSeek/本地模型）
2. 需要哪些内置 Tool？（默认：查用户信息、查角色、查菜单、查组织、查岗位、查租户）
3. 是否开启历史消息？（默认开启，保留 20 轮）
核心能力清单
| # | 能力 | 说明 |
|---|---|---|
| 1 | Spring AI Agent | 基于 Spring AI ChatClient + Function Calling，支持节点扩展 |
| 2 | Tool 系统 | 声明式 Tool 定义，Jakarta Bean Validation 参数校验，自动权限注入 |
| 3 | 模型接入 | 统一 ChatModel 接口，支持 OpenAI/Claude/DeepSeek/Ollama，Resilience4j 退避重试 |
| 4 | 多轮对话 | 上下文记忆，会话级别历史，Deque 自动裁剪 + LRU 内存缓冲 |
| 5 | 对话管理 | 创建/查询/删除/清除会话（软删除 + 级联硬删除） |
| 6 | 租户隔离 | org_tools 全部按 tenant 过滤，多租户安全 |
| 7 | 流式输出 | SseEmitter 流式返回 token，含断连检测 + 代理缓冲禁用 |
| 8 | Rate Limiting | Bucket4j 实现，每用户 10 次/分钟（防 LLM 财务风险） |
| 9 | 审计日志 | 独立 agent.audit logger，记录 tool_call/tool_failure/chat_failure/token_usage/rate_limit_hit |
| 10 | 异常脱敏 | 客户端仅收到固定话术，真实异常写入服务端 log.error() |
| 11 | 数据库索引 | Flyway 迁移含 5 个关键索引（user_updated / user_deleted / session_created / session_role / user_id） |
| 12 | 事务一致性 | chat() 单事务写入用户/助手消息，无幽灵消息 |
| 13 | 测试基建 | src/test/ 提供 20+ 安全/一致性/性能测试 |
| 14 | Prompt Injection 防护 | Tool 结果用 XML 标签包裹，System Prompt 明确隔离指令 |
| 15 | PII 加密 | Fernet 对称加密（AES-128-CBC + HMAC-SHA256），日志自动脱敏 |
| 16 | trace_id 关联 | MDC 注入 trace_id，跨服务追踪支持 |
| 17 | 安全响应头 | 复用骨架 SecurityConfig（X-Content-Type-Options / X-Frame-Options 等） |
| 18 | 模型白名单 | 客户端无法指定白名单外模型（防财务/审计风险） |
What ships with it
18 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.
- api-contract-agent.md 6.2 KB
- README.md 7.4 KB
- references/agent-runner.java 7.8 KB
- references/agent.properties 1.2 KB
- references/agent.sql 4.1 KB
- references/audit.java 2.2 KB
- references/config.java 3.9 KB
- references/controller.java 5.6 KB
- references/enums.java 952 B
- references/memory.java 3.5 KB
- references/models.java 2.9 KB
- references/org-tools.java 5.2 KB
- references/pii.java 4.3 KB
- references/rate-limiter.java 9.8 KB
- references/security-filters.java 3.0 KB
- references/tool-executor.java 4.4 KB
- references/tools.java 6.2 KB
- references/user-tools.java 3.4 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.
- 3d ago Changed · +471 lines · +34 tokens per session 35379f59664c
- 9d ago First seen · 237 lines · 116 tokens per session scan A 2696cc8f5e7d
springboot-agent-module-skill is a skill published in the GitHub repository jiushiwon/wg-skills (97 stars, last pushed 2d ago), licensed Apache-2.0. It adds 150 tokens to every session and 8,880 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 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.