Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kora-projects/kora-skillsnpx agentmods add skills/kora-projects/kora-skills/kora-database-jdbcWrote 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/kora-projects/kora-skills/kora-database-jdbc)<a href="https://agentmods.dev/skills/kora-projects/kora-skills/kora-database-jdbc"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-database-jdbc/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/kora-projects/kora-skills/kora-database-jdbc"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-database-jdbc.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 | $0.00060 | $0.02891 |
| Opus 5 | $0.00030 | $0.01445 |
| Sonnet 5 | $0.00012 | $0.00578 |
| Haiku 4.5 | $0.00006 | $0.00289 |
Grade A, and why
kora-database-jdbc 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 8d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kora Database JDBC
Kora sub-skill — obey the kora-v1 meta rules on every task: R0 ensure
.kora-agent/docs+examples are cloned · R1 read this sub-skill before writing code · R2 Kora APIs only — no Spring/Micronaut/Quarkus, no invented annotations or config keys · R3 journal any incorrect Kora usage. Add comments/Javadoc only if asked.
JDBC-based relational database access (PostgreSQL, MySQL, Oracle) with HikariCP. Repositories are @Repository interfaces whose implementations are generated at compile time by the annotation processor — no reflection, no runtime proxies.
Prefer synchronous repository signatures (
Entity,@Nullable Entity,List<Entity>,UpdateCount). The blocking JDBC driver runs on the executor bound toJdbcDatabase; virtual threads or a fixed pool handle blocking efficiently. Reach forCompletionStage/Monoonly when a downstream contract requires it.
Quick Start
1. Dependencies (build.gradle)
dependencies {
koraBom platform("ru.tinkoff.kora:kora-parent:1.2.19")
annotationProcessor "ru.tinkoff.kora:annotation-processors" // mandatory: generates *RepositoryImpl
implementation "ru.tinkoff.kora:database-jdbc"
implementation "ru.tinkoff.kora:config-hocon"
implementation "ru.tinkoff.kora:logging-logback"
implementation "org.postgresql:postgresql:42.7.7" // JDBC driver is required (not bundled)
}
All ru.tinkoff.kora:* artifacts inherit their version from the kora-parent BOM — never pin them individually.
Kotlin: use ksp "ru.tinkoff.kora:symbol-processors" instead of annotationProcessor, and implementation("...") syntax.
2. Plug the module into @KoraApp
@KoraApp
public interface Application extends
HoconConfigModule,
LogbackModule,
JdbcDatabaseModule { }
JdbcDatabaseModule provides JdbcDatabase, its JdbcConnectionFactory, and the JdbcDatabaseConfig reader bound to the db config section.
What ships with it
24 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.
- assets/jdbc-crud-abstract-macros-repository.java.template 3.3 KB
- assets/jdbc-crud-abstract-single-id-macros-repository.kt.template 3.4 KB
- assets/jdbc-crud-composite-id-repository.java.template 4.6 KB
- assets/jdbc-crud-composite-id-repository.kt.template 3.2 KB
- assets/jdbc-crud-single-id-repository.java.template 4.2 KB
- assets/jdbc-crud-single-id-repository.kt.template 2.0 KB
- assets/jdbc-entity-composite-id.java.template 2.5 KB
- assets/jdbc-entity-composite-id.kt.template 1.2 KB
- assets/jdbc-entity-single-id.java.template 2.2 KB
- assets/jdbc-entity-single-id.kt.template 1.8 KB
- assets/jdbc-repository-with-array-mapper.java.template 3.8 KB
- assets/jdbc-repository-with-enum-mapper.java.template 3.9 KB
- assets/jdbc-repository-with-enum-mapper.kt.template 3.2 KB
- assets/jdbc-service-with-transactions.java.template 4.8 KB
- evals/evals.json 7.0 KB
- references/connection-pool-reference.md 3.3 KB
- references/custom-mappers-advanced-reference.md 9.4 KB
- references/custom-mappers-reference.md 8.7 KB
- references/database-jdbc-config-reference.md 4.8 KB
- references/entity-mapping-reference.md 7.6 KB
- references/migrations-reference.md 7.4 KB
- references/repository-pattern-reference.md 11 KB
- references/transactions-reference.md 6.4 KB
- scripts/generate_repository.py 6.0 KB runs code
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.
- 8d ago First seen · 262 lines · 60 tokens per session scan A 72e65737750b
kora-database-jdbc is a skill published in the GitHub repository kora-projects/kora-skills (1 stars, last pushed 8d ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,891 once invoked, about $0.0003 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 skills, from other repositories
azure-data-tables-java
Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.
azure-cosmos-java
Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns. Triggers: "CosmosClient java", "CosmosAsyncClient", "cosmos database java", "cosmosdb java", "document database java".
jpa-patterns
JPA/Hibernate patterns and common pitfalls (N+1, lazy loading, transactions, queries). Use when user has JPA performance issues, LazyInitializationException, or asks about entity relationships and fetching strategies.
neo4j-driver-java-skill
Neo4j Java Driver v6 — driver lifecycle, Maven/Gradle setup, executableQuery, executeRead/Write managed transactions, explicit transactions, async/reactive patterns, error handling, data type mapping, connection pool tuning, causal consistency/bookmarks. Use when writing Java or Kotlin code that connects to Neo4j via…
311-frameworks-spring-jdbc
Use when you need to write or review programmatic JDBC with Spring — including JdbcClient (Spring Framework 7+) as the default API, JdbcTemplate only where batch/streaming APIs require JdbcOperations, NamedParameterJdbcTemplate for legacy named-param code, parameterized SQL, RowMapper mapping to records, batch…
312-frameworks-spring-data-jdbc
Use when you need to use Spring Data JDBC with Java records — including entity design with records, repository pattern, immutable updates, aggregate relationships, custom queries, transaction management, and avoiding N+1 problems. This should trigger for requests such as Review Java code for Spring Data JDBC; Apply…