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 agentmods add skills/seed-forge/harness-ai-kit/devlab-dao-sql-compatnpx skills add seed-forge/harness-ai-kit --skill devlab-dao-sql-compatgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/devlab-dao-sql-compat)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/devlab-dao-sql-compat"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/devlab-dao-sql-compat.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 | $0.00160 | $0.02455 |
| Opus 5 | $0.00080 | $0.01228 |
| Sonnet 5 | $0.00032 | $0.00491 |
| Haiku 4.5 | $0.00016 | $0.00246 |
Grade A, and why
devlab-dao-sql-compat 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devlab-dao-sql-compat
用途
面向使用任何持久层框架（MyBatis / JPA / MyBatis-Plus / SQLAlchemy）的项目，解决"同一套 DAO 代码需要运行在不同数据库（Oracle / PostgreSQL / MySQL）"或"数据库迁移"场景下的 SQL 方言兼容性问题：
- 检查：通过 adapter 模式扫描框架专属源码文件，按模块输出三方言命中矩阵与风险分级
- 修复：AI 按转换方向加载对应映射表（references/dialects/），逐模块修复
- 验证：静态复扫必做，库级语法预检可选，明确降级声明
- 记录：输出前后对比与待人工复核清单
支持三方言全对称 6 个转换方向：O→PG、PG→O、O→MySQL、MySQL→O、PG→MySQL、MySQL→PG。
框架探测
本技能支持 4 种 DAO 框架的 adapter，默认自动探测：
| 检测特征 | 判定框架 | 扫描目标 |
|---|---|---|
**/mapper/**/*.xml 含 SQL 标签 |
MyBatis | Mapper XML |
**/*.java 含 @Query / @NamedQuery |
JPA/Hibernate | Java 源码 |
**/*.java 含 QueryWrapper / LambdaQueryWrapper / BaseMapper |
MyBatis-Plus | Java + XML |
**/*.py 含 text() / .execute() / session.execute |
SQLAlchemy | Python 源码 |
| 多个命中 | 提示用户选择 | monorepo 可能多框架 |
也可手动指定：bash scripts/scan-sql-compat.sh --adapter mybatis
各框架的扫描模式、提取逻辑和方言陷阱详见 references/adapters/ 下对应文档。
配置上下文
本 Skill 的运行时配置遵循 harness-ai-kit 配置治理规范的三级优先级：
L3 对话中用户明确声明的参数 > L2 用户配置（~/.harness-ai-kit/config.yaml → 环境变量 → ~/.harness-ai-kit/.env.tak）> L1 本目录 config.defaults.yaml
配置项见 config.defaults.yaml：adapter / scan_dir / module_glob / report_path / custom_procs_file / fail_on_critical / verify_jdbc_url。
其中 verify_jdbc_url 为 sensitive：无默认值，只能经 L2/L3 注入，禁止写入任何文档或提交。
工作流（七阶段）
Phase 0 环境确认
- 确认 DAO 框架类型（auto-detect 或手动
--adapter） - 确认扫描根目录（scan_dir）；框架专属源码位置默认自动探测，非标准布局时向用户确认 module_glob
- 向用户确认目标方言拓扑（二选一）：
- 单一目标库：整个项目最终只跑一种数据库 → 所有非目标方言都是待修复项
- 多库路由：不同模块路由到不同数据库 → 逐模块建立"模块 → 目标方言"映射表
- 询问是否有自定义存储过程/函数（写入 custom_procs_file 清单）
Phase 1 扫描
bash <本Skill目录>/scripts/scan-sql-compat.sh \
--adapter <auto|mybatis|jpa|mybatis-plus|sqlalchemy> \
--dir <scan_dir> [--module-glob <glob>] [--procs <file>] --report <report_path>
产出报告含：三方言命中明细、模块级风险矩阵、自定义存储过程依赖。 风险等级：CRITICAL（同模块方言混用）/ HIGH（单方言文件数 >5）/ MEDIUM（单方言文件数 ≤5）。
Phase 2 范围决策
向用户呈现风险矩阵，确认本次修复范围（CRITICAL 优先，或用户指定模块）。禁止全量静默修复。
What ships with it
29 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.
- CHANGELOG.md 5.1 KB
- config.defaults.yaml 2.0 KB
- examples/mybatis/after/sample-mapper.xml 2.1 KB
- examples/mybatis/before/sample-mapper.xml 2.1 KB
- examples/mybatis/README.md 1.6 KB
- README.md 6.2 KB
- references/adapters/jpa.md 1.9 KB
- references/adapters/mybatis-plus.md 2.4 KB
- references/adapters/mybatis.md 1.8 KB
- references/adapters/sqlalchemy.md 2.6 KB
- references/dialects/mysql-to-oracle.md 1.7 KB
- references/dialects/mysql-to-postgres.md 1.6 KB
- references/dialects/oracle-to-mysql.md 1.7 KB
- references/dialects/oracle-to-postgres.md 3.1 KB
- references/dialects/postgres-to-mysql.md 1.6 KB
- references/dialects/postgres-to-oracle.md 2.7 KB
- references/REFERENCE-VERIFICATION.md 1.7 KB
- references/systematic-fixes/coalesce-nullstr.sed 520 B
- references/systematic-fixes/regex-operator.sed 757 B
- references/systematic-fixes/todate-concat.sed 904 B
- references/systematic-fixes/todate-format-guide.md 2.3 KB
- scripts/adapters/jpa.sh 2.8 KB runs code
- scripts/adapters/mybatis-plus.sh 3.3 KB runs code
- scripts/adapters/mybatis.sh 2.1 KB runs code
- scripts/adapters/sqlalchemy.sh 3.0 KB runs code
- scripts/fix-sql-compat.sh 9.8 KB runs code
- scripts/scan-sql-compat.sh 13 KB runs code
- skill.json 3.1 KB
- USAGE.md 2.6 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 First seen · 153 lines · 160 tokens per session scan A 653b26a5f8a8
devlab-dao-sql-compat is a skill published in the GitHub repository seed-forge/harness-ai-kit (21 stars, last pushed 7d ago), licensed Apache-2.0. It adds 160 tokens to every session and 2,455 once invoked, about $0.0008 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
database-design
Designs database schemas, indexing strategies, query optimization, and migration patterns for SQL and NoSQL databases. Use when designing tables, optimizing queries, fixing N+1 problems, planning migrations, or when asked about database performance, normalization, ORMs, or data modeling.
relational-database-mcp-cloudbase
Sibling CloudBase skills ship beside this skill. Use local relative paths such as ../auth-tool-cloudbase/SKILL.md.
cloudbase-all-in-one
Unified CloudBase execution guide for all-in-one skill installs. Use this first for CloudBase app tasks, especially existing apps with TODOs, fixed pages, or active handlers. Routes PostgreSQL / CloudBase PG / app.rdb() / queryPgDatabase / managePgDatabase work away from legacy NoSQL and old auth patterns.
cloudbase-document-database-in-wechat-miniprogram
Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.
architect/data-api-design
Skill "architect/data-api-design" from echoVic/boss-skill, covering 数据模型与api设计方法论, 适用场景, 数据模型设计, 1. 实体识别 and 2. 关系识别.
cloudbase-cli
CloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. Use when deploying cloud functions, CloudRun, storage, NoSQL/MySQL, static hosting, permissions, CORS/domains via tcb; for CI/CD and batch ops; when the user prefers CLI; or as the first-session fallback when CloudBase MCP tools are not…