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 cdppcorp/KESE-KIT --skill kesekit-guide-kogit clone --depth 1 https://github.com/cdppcorp/KESE-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/cdppcorp/kese-kit/kesekit-guide-ko)<a href="https://agentmods.dev/skills/cdppcorp/kese-kit/kesekit-guide-ko"><img src="https://agentmods.dev/badge/skills/cdppcorp/kese-kit/kesekit-guide-ko.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 5.1 | $0.00121 | $0.02369 |
| Opus 5 | $0.00060 | $0.01184 |
| Sonnet 5 | $0.00024 | $0.00474 |
| Haiku 4.5 | $0.00012 | $0.00237 |
Grade A, and why
kesekit-guide-ko 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KESE 시큐어 코딩 프롬프트 생성기
KISA 가이드라인과 국제 표준(OWASP, CWE)을 기반으로 AI 도구용 시큐어 코딩 프롬프트를 생성합니다.
가이드라인 선택
| # | 가이드라인 | 설명 |
|---|---|---|
| 1 | CII 시큐어코딩 | 전통적 보안 취약점 (SQL Injection, XSS 등) |
| 2 | AI 보안 시큐어코딩 | AI 특화 보안 (Prompt Injection, 데이터 중독 등) |
| 3 | 로봇 보안 시큐어코딩 | 로봇 특화 보안 (IEC 62443, 펌웨어, 통신 프로토콜) |
| 4 | 우주 보안 시큐어코딩 | 우주 특화 보안 (CCSDS, 위성 프로토콜, GSaaS, 공급망) |
| 5 | 시큐어코딩 (언어별) | 언어별 시큐어코딩 (JS, Python, pseudo code) |
| 6 | 제로트러스트 가이드 | 제로트러스트 아키텍처 및 성숙도 평가 가이드 (8개 핵심요소, ~396항목) |
웹/서버/DB 개발 → CII / AI 모델/LLM/AI 서비스 개발 → AI 보안 / 로봇 펌웨어, ROS/ROS2, 로봇 API, 산업 프로토콜 개발 → 로봇 보안 / 위성 통신, 지상국, GSaaS API, 우주 공급망 → 우주 보안 / JavaScript, Python, 기타 언어 → 시큐어코딩 (언어별) Zero Trust, ZTA, ZTNA, 제로트러스트, 마이크로세그멘테이션, microsegmentation, SDP, SASE, PEP/PDP, never trust always verify → 제로트러스트
CII 분기 시
templates/cii/webapp.md를 참조하여 CWE 기반 시큐어 코딩 프롬프트를 생성합니다. 점검/수정 스크립트는 scripts/cii/에 있습니다.
실행 흐름
- 사용자에게 대상 컨텍스트 확인 (언어, 프레임워크, 기능 유형)
- 커스터마이징된 시큐어 코딩 프롬프트 생성
- 관련 CWE 패턴 및 KISA 가이드라인 포함
- 복사-붙여넣기 형식으로 프롬프트 제공
주요 CWE 패턴
| CWE | 이름 | 방지 방법 |
|---|---|---|
| CWE-20 | 부적절한 입력 검증 | 모든 입력 검증 |
| CWE-22 | 경로 조작 | 경로 정규화 및 검증 |
| CWE-78 | OS Command Injection | shell 피하기, 인자 리스트 |
| CWE-79 | XSS | 출력 인코딩, CSP |
| CWE-89 | SQL Injection | 매개변수화된 쿼리 |
| CWE-94 | Code Injection | eval(), exec() 피하기 |
| CWE-287 | 부적절한 인증 | 검증된 프레임워크 사용 |
| CWE-327 | 약한 암호화 | AES-256, RSA-2048+ |
| CWE-352 | CSRF | CSRF 토큰 |
| CWE-434 | 무제한 업로드 | 타입, 크기, 이름 검증 |
| CWE-502 | 안전하지 않은 역직렬화 | JSON 사용 |
| CWE-611 | XXE | 외부 엔티티 비활성화 |
| CWE-798 | 하드코딩된 자격 증명 | 환경 변수 사용 |
| CWE-918 | SSRF | URL 검증, 사설 IP 차단 |
언어별 프롬프트 생성
사용자가 지정한 언어에 맞게 시큐어 코딩 프롬프트를 생성합니다:
- Python: SQL Injection, Command Injection, 경로 조작, 역직렬화, 패스워드 해싱
- JavaScript/Node.js: XSS, SQL Injection, Command Injection, 안전한 난수
- Java: SQL Injection, XXE, 경로 조작, 역직렬화
- Go, Rust, C# 등 요청 시 해당 언어에 맞게 생성
기능별 프롬프트 생성
- 인증 구현, 파일 업로드, API 보안, 세션 관리 등
What ships with it
60 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.
- references/ai-security/overview.md 5.3 KB
- references/ai-security/service-provider.md 2.6 KB
- references/ai-security/user-guide.md 2.4 KB
- references/secure-coding/overview.md 5.3 KB
- references/secure-coding/pseudocode.md 25 KB
- references/space-security/overview.md 4.2 KB
- references/space-security/supply-chain.md 1.6 KB
- references/zero-trust/maturity-model.md 2.3 KB
- references/zero-trust/ot-guide.md 6.4 KB
- references/zero-trust/overview.md 4.4 KB
- scripts/ai-security/api-security-check.md 4.0 KB
- scripts/ai-security/data-pipeline-check.md 4.1 KB
- scripts/ai-security/model-security-check.md 2.8 KB
- scripts/cii/cloud.md 19 KB
- scripts/cii/database.md 15 KB
- scripts/cii/network.md 20 KB
- scripts/cii/pc.md 11 KB
- scripts/cii/unix.md 39 KB
- scripts/cii/web-service.md 19 KB
- scripts/cii/webapp.md 27 KB
- scripts/cii/windows.md 49 KB
- scripts/robot-security/cert-and-protocol.md 2.3 KB
- scripts/robot-security/firewall-hardening.md 2.3 KB
- scripts/robot-security/resource-management.md 2.2 KB
- scripts/robot-security/sbom-audit.md 1.9 KB
- scripts/zero-trust/identity-check.md 4.0 KB
- scripts/zero-trust/network-check.md 4.0 KB
- scripts/zero-trust/visibility-check.md 4.2 KB
- templates/ai-security/developer.md 11 KB
- templates/ai-security/service-provider.md 3.8 KB
- templates/ai-security/user-guide-checklist.md 655 B
- templates/cii/admin.md 4.3 KB
- templates/cii/cloud.md 1.6 KB
- templates/cii/control-system.md 3.8 KB
- templates/cii/database.md 2.1 KB
- templates/cii/mobile.md 502 B
- templates/cii/network.md 2.4 KB
- templates/cii/pc.md 1.6 KB
- templates/cii/physical.md 1.6 KB
- templates/cii/security-equip.md 1.8 KB
- templates/cii/unix.md 4.7 KB
- templates/cii/virtualization.md 1.7 KB
- templates/cii/web-service.md 2.1 KB
- templates/cii/webapp.md 1.5 KB
- templates/cii/windows.md 4.6 KB
- templates/robot-security/cyber-resilience.md 1.1 KB
- templates/robot-security/iec62443.md 3.9 KB
- templates/robot-security/overview.md 3.7 KB
- templates/robot-security/ssdf.md 2.0 KB
- templates/robot-security/supply-chain.md 982 B
- templates/robot-security/wireless.md 1.3 KB
- templates/secure-coding/javascript.md 42 KB
- templates/secure-coding/python.md 54 KB
- templates/space-security/access-control.md 3.8 KB
- templates/space-security/governance.md 5.1 KB
- templates/space-security/operations.md 3.8 KB
- templates/space-security/supply-chain.md 2.6 KB
- templates/space-security/system-security.md 3.5 KB
- templates/zero-trust/app-data.md 22 KB
- templates/zero-trust/identity-device.md 16 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.
- 8d ago First seen · 145 lines · 121 tokens per session scan A 0aaf52674384
kesekit-guide-ko is a skill published in the GitHub repository cdppcorp/KESE-KIT (356 stars, last pushed 5mo ago), licensed MIT. It adds 121 tokens to every session and 2,369 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…