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-starterWrote 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-starter)<a href="https://agentmods.dev/skills/kora-projects/kora-skills/kora-starter"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-starter/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-starter"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-starter.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 | $0.00268 | $0.04573 |
| Opus 5.5 | $0.00107 | $0.01829 |
| Sonnet 5.5 | $0.00054 | $0.00915 |
| Haiku 4.5 | $0.00027 | $0.00457 |
Grade C, and why
kora-v1 scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .kora-agent/kora-docs/.git .kora-agent/kora-examples/.git This is a copy
89% identical to kora-v1 — 92 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kora Framework — Meta-skill
Single entry point for all Kora development. This file is routing and rules only — the implementation knowledge lives in the 39 sub-skills listed below.
| Framework | Kora 1.x (ru.tinkoff.kora) — check the changelog for the current release |
| Java | 17+ supported, 25+ recommended (annotation processors) |
| Kotlin | 1.9+ on JDK 21 (KSP) |
| Build | Gradle 7+ supported, 9+ recommended (wrapper pins 9.5.1) |
This meta-skill is the single entry point for Kora Framework development. It routes to 39 specialized domain skills, each with its own narrow area of expertise.
Read this file first when:
- Starting a new Kora microservice project from scratch (Java or Kotlin)
- Adding or refactoring
@KoraAppapplication graph with*Moduleinterfaces - Choosing which Kora modules to plug in (HTTP, Database, Kafka, gRPC, SOAP, S3, Telemetry)
- Debugging DI container issues ("dependency not found", ambiguous bindings, graph build failures)
- Configuring typed config with
@ConfigSourceand environment variable substitution - Planning a multi-module Gradle project with
@KoraSubmoduleboundaries
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.
- 2mo ago First seen · 293 lines · 268 tokens per session scan C 0e765e9ec321
kora-v1 is a skill published in the GitHub repository kora-projects/kora-skills (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 268 tokens to every session and 4,573 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). It is 89% identical to kora-v1, differing in 92 lines, and is treated as a copy.
Other skills, from other repositories
authoring-java-sdk-tasks
Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…
null-safety
Use when annotating nullability in Spring Boot 3 / Spring Framework 6 code, integrating Kotlin, or adding static nullability checks without assuming Spring Framework 7 JSpecify defaults.
spring-boot-idioms
Spring Boot 3.x framework patterns: constructor-based DI, Spring Data JPA, REST controllers with RFC 7807 error handling, Actuator observability, and slice testing. Use when building or maintaining Spring Boot microservices. Pair with java-idioms.
kotlin-backend-conventions
A set of coding conventions for BK-CI Kotlin back-end projects. Kotlin is a programming language, and back-end code runs the services behind an application.
backend-microservice-development
Backend microservice development guidance for BK-CI using Kotlin or Java and Spring Boot. It covers resources, API, service, and data-access layers, dependency injection, service ownership, and backend conventions.
cratis-chronicle-client-kotlin
Use when connecting a standalone Kotlin or Java application to Chronicle, including client registration and lifecycle issues. Not for Arc commands, Elixir OTP or Node.js clients.