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-di-compileWrote 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-di-compile)<a href="https://agentmods.dev/skills/kora-projects/kora-skills/kora-di-compile"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-di-compile/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-di-compile"><img src="https://agentmods.dev/badge/skills/kora-projects/kora-skills/kora-di-compile.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 | $0.00063 | $0.01738 |
| Opus 5 | $0.00032 | $0.00869 |
| Sonnet 5 | $0.00013 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
kora-di-compile 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 12d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kora DI Compile — Compile-Time Dependency Injection
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.
Version: Kora 1.x | Java: 25+ | Kotlin: 1.9+ | Gradle: 9+
Kora uses compile-time code generation — all dependency wiring happens at compile time via annotation processors. No reflection, no runtime proxies. Errors are caught at compile time, not runtime.
Read this skill when: bootstrapping @KoraApp, creating @Component/@Module, multi-module projects with @KoraSubmodule, debugging DI errors ("no factory found", "ambiguous dependency", circular dependencies).
Quick Start
Task Progress:
- [ ] 1. Add Kora BOM and annotation processor to build.gradle
- [ ] 2. Create @KoraApp interface with main() entry point
- [ ] 3. Extend required modules (HoconConfigModule, LogbackModule)
- [ ] 4. Create @Component classes with constructor injection
- [ ] 5. Run ./gradlew classes to generate ApplicationGraph
1. Build Setup
plugins { id "java"; id "application" }
configurations {
koraBom
annotationProcessor.extendsFrom(koraBom)
implementation.extendsFrom(koraBom)
}
dependencies {
koraBom platform("ru.tinkoff.kora:kora-parent:1.2.19")
annotationProcessor "ru.tinkoff.kora:annotation-processors"
implementation "ru.tinkoff.kora:config-hocon"
implementation "ru.tinkoff.kora:logging-logback"
}
java { sourceCompatibility = JavaVersion.VERSION_25 }
application { mainClass = "com.example.Application" }
2. Application Bootstrap
@KoraApp
public interface Application extends HoconConfigModule, LogbackModule {
static void main(String[] args) {
KoraApplication.run(ApplicationGraph::graph);
}
}
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/application.conf.template 251 B
- assets/Application.java.template 947 B
- assets/Application.kt.template 813 B
- assets/application.yaml.template 431 B
- assets/build.gradle.kts.template 1.5 KB
- assets/build.gradle.template 1.4 KB
- assets/Component.java.template 988 B
- assets/gradle-wrapper.properties.template 252 B
- assets/gradle.properties.template 307 B
- assets/KoraSubmodule.java.template 1.2 KB
- assets/Module.java.template 1.3 KB
- assets/QUICK_REFERENCE.md 2.9 KB
- assets/settings.gradle.template 542 B
- evals/evals.json 7.0 KB
- references/component-factories-reference.md 8.7 KB
- references/component-registration-reference.md 7.2 KB
- references/default-component-reference.md 8.3 KB
- references/kora-app-component-reference.md 4.7 KB
- references/kora-submodule-reference.md 10 KB
- references/lifecycle-reference.md 14 KB
- references/module-auto-discovery-reference.md 6.4 KB
- references/tags-collections-reference.md 8.7 KB
- scripts/generate_project.py 15 KB runs code
- scripts/validate_gradle.py 8.0 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.
- 12d ago First seen · 253 lines · 63 tokens per session scan A 0ffeb4271b1d
kora-di-compile is a skill published in the GitHub repository kora-projects/kora-skills (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,738 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
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.
horse-lazarus-compatibility
Guide for ensuring Lazarus and Free Pascal (FPC) compatibility, addressing anonymous methods differences, JSON units, and compiler directives.
horse-performance-tuning
Guide for optimizing performance, tuning memory alocations, handling large payloads, and adjusting provider execution pipelines.