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-fix-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-fix-ko)<a href="https://agentmods.dev/skills/cdppcorp/kese-kit/kesekit-fix-ko"><img src="https://agentmods.dev/badge/skills/cdppcorp/kese-kit/kesekit-fix-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 | $0.00119 | $0.01796 |
| Opus 5 | $0.00060 | $0.00898 |
| Sonnet 5 | $0.00024 | $0.00359 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade A, and why
kesekit-fix-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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KESE 취약점 자동 수정
취약점 분석 결과를 기반으로 적절한 수정을 생성하고 적용합니다. 사용자의 환경에 맞는 가이드라인을 자동 선택합니다.
가이드라인 선택
| # | 가이드라인 | 설명 |
|---|---|---|
| 1 | CII 하드닝 | 플랫폼별 하드닝 스크립트 생성 |
| 2 | AI 보안 조치 | AI 시스템 보안 강화 가이드 |
| 3 | 로봇 보안 조치 | 로봇 시스템 보안 강화 (IEC 62443, CRA, RED) |
| 4 | 우주 보안 조치 | 우주 시스템 하드닝 (CMMC, K-RMF, NIS2, NIST IR 8401) |
| 5 | 시큐어코딩 수정 | 취약 코드 패턴 자동 수정 (JS/Python, 46 CWE) |
| 6 | 제로트러스트 조치 | 제로트러스트 갭 분석 기반 조치 가이드 (8개 핵심요소, ~396항목) |
서버, 인프라, 웹 서비스, DB → CII / AI 모델, LLM, AI 서비스 → AI 보안 / 로봇, ROS/ROS2, 로봇 펌웨어, 무선 제어 인터페이스 → 로봇 보안 / 위성, 지상국, GSaaS, 우주 공급망 → 우주 보안 / JavaScript, Python, 웹 앱 코드 → 시큐어코딩 Zero Trust, ZTA, ZTNA, 제로트러스트, 마이크로세그멘테이션, microsegmentation, SDP, SASE, PEP/PDP, never trust always verify → 제로트러스트
CII 분기 시
실행 흐름
reports/kese/에서 이전 평가 결과 읽기 (있는 경우)- 이전 평가가 없으면 사용자에게 대상 플랫폼 확인
- 해당 템플릿 파일을
templates/cii/에서 로드 (점검/수정 스크립트는scripts/cii/에 있음) - 플랫폼별 하드닝 스크립트 생성
- 스크립트를
scripts/kese-hardening/에 저장
출력 구조
scripts/kese-hardening/
├── unix/ ← bash 스크립트
├── windows/ ← PowerShell 스크립트
├── web/ ← Apache/Nginx 설정
├── database/ ← SQL 스크립트
└── README.md
플랫폼별 reference 매핑
| 플랫폼 | reference | 스크립트 유형 |
|---|---|---|
| Unix/Linux | templates/cii/unix.md |
bash |
| Windows | templates/cii/windows.md |
PowerShell |
| 웹 서비스 | templates/cii/web-service.md |
conf 파일 |
| DBMS | templates/cii/database.md |
SQL |
| 네트워크 장비 | templates/cii/network.md |
CLI 명령어 |
| 보안 장비 | templates/cii/security-equip.md |
설정 가이드 |
| PC | templates/cii/pc.md |
PowerShell/GPO |
| 클라우드 | templates/cii/cloud.md |
CLI 명령어 |
수정 적용 시 주의사항
- 수정 전 항상 설정 백업
- 비운영 환경에서 먼저 테스트
- 일부 수정은 서비스 재시작 필요
- 컴플라이언스 감사를 위해 모든 변경사항 문서화
AI 보안 분기 시
실행 흐름
references/ai-security/overview.md를 읽어 AI 보안 위협 유형 파악- 대상에 따라 적절한 reference 로드
- 보안 강화 가이드 및 코드 패치 생성
대상별 조치
| 대상 | reference | 조치 내용 |
|---|---|---|
| AI 개발자 | templates/ai-security/developer.md |
모델 보안, 데이터 보호, API 보안 코드 |
| 서비스 제공자 | references/ai-security/service-provider.md |
서비스 보안 설정, 접근통제 |
| AI 이용자 | references/ai-security/user-guide.md |
보안 수칙 적용 체크리스트 |
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/space-security/access-control-fix.md 6.0 KB
- scripts/space-security/operations-fix.md 4.6 KB
- scripts/space-security/system-security-fix.md 6.3 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
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.
- 9d ago First seen · 134 lines · 119 tokens per session scan A eefdeec3fa3c
kesekit-fix-ko is a skill published in the GitHub repository cdppcorp/KESE-KIT (356 stars, last pushed 5mo ago), licensed MIT. It adds 119 tokens to every session and 1,796 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-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…