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 composite/korean-skills --skill egovframe-compatibilitygit clone --depth 1 https://github.com/composite/korean-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/composite/korean-skills/egovframe-compatibility)<a href="https://agentmods.dev/skills/composite/korean-skills/egovframe-compatibility"><img src="https://agentmods.dev/badge/skills/composite/korean-skills/egovframe-compatibility/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/composite/korean-skills/egovframe-compatibility"><img src="https://agentmods.dev/badge/skills/composite/korean-skills/egovframe-compatibility.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 | $0.00055 | $0.01750 |
| Opus 5.5 | $0.00022 | $0.00700 |
| Sonnet 5.5 | $0.00011 | $0.00350 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
egovframe-compatibility 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 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.
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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eGovFrame Compatibility Rules
Overview
eGovFrame 4.x/5.x adds constraints on top of Spring conventions for government system development. Only eGovFrame-specific rules are documented here — Spring Framework knowledge assumed.
Scope: Java projects using org.egovframe.rte.* (eGovFrame 4.x+). Excludes egovframework.rte.* (3.10 and earlier), non-Java code, and frontend concerns.
Controller Layer
Target: @Controller, @RestController, and Servlet code only when Spring MVC is impractical and justified.
Rules:
- Map handlers with Spring MVC annotations.
- Do not inject or call DAO classes directly, including subclasses of
SqlMapClientDaoSupport,SqlSessionDaoSupport, andHibernateDaoSupport. - No direct NoSQL, MQ, or cache access from controllers.
- Route business logic through an injected service interface.
// ✅ Correct
@Controller
@RequestMapping("/sample")
public class SampleController {
@Autowired
private SampleService sampleService;
@GetMapping("/list")
public String list(Model model) {
model.addAttribute("list", sampleService.selectList());
return "sample/list";
}
}
// ❌ DAO injected directly — forbidden
@Controller
public class SampleController {
@Autowired
private SampleMapper sampleMapper; // ❌ inject Service, not DAO
}
// ❌ Business logic handled inside controller — forbidden
@GetMapping("/calc")
public String calc(Model model) {
int result = heavyBusinessCalculation(); // ❌ delegate to Service
model.addAttribute("result", result);
return "sample/result";
}
Service Layer
Target: @Service or @Component business classes, excluding tests.
Rules:
- Each service implementation must extend
EgovAbstractServiceImpl, directly or through a base class. - Each service implementation must implement a dedicated service interface.
Why the interface matters: eGovFrame AOP relies on Java Dynamic Proxy, not CGLIB — class-only services cannot be proxied.
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 · 252 lines · 55 tokens per session scan A 940542d307a3
egovframe-compatibility is a skill published in the GitHub repository composite/korean-skills (4 stars, last pushed 29d ago), licensed MIT. It adds 55 tokens to every session and 1,750 once invoked, about $0.0002 per session on Opus 5.5. 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.
egovframe-compatibility compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| egovframe-compatibilitycomposite/korean-skills | Skill | 4 | 29d ago | MIT | A | 55 | Claude Code, Codex |
| remove-deprecated-apiadobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 174 | Claude Code |
| outbound-call-timeoutsadobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 151 | Claude Code |
| outdated-dependenciesadobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 93 | Claude Code |
| inject-in-sling-modeladobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 126 | Claude Code |
| authoring-java-sdk-tasksastronomer/agents | Skill | 458 | 4d ago | Apache-2.0 | A | 152 | Claude Code |
| configuring-airflow-language-sdksastronomer/agents | Skill | 458 | 4d ago | Apache-2.0 | A | 155 | Claude Code |