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 modu-ai/moai-cowork --skill legal-mfds-safetygit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/legal-mfds-safety)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/legal-mfds-safety"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/legal-mfds-safety/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/modu-ai/moai-cowork/legal-mfds-safety"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/legal-mfds-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00321 | $0.02368 |
| Opus 5 | $0.00161 | $0.01184 |
| Sonnet 5 | $0.00064 | $0.00474 |
| Haiku 4.5 | $0.00032 | $0.00237 |
Grade A, and why
legal-mfds-safety scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
## 실행 예시 (curl) How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MFDS 의약품·식품 안전 체크 (통합)
식품의약품안전처(MFDS) 공식 OpenAPI를 통해 의약품과 식품의 안전 정보를 확인합니다. 헬스·F&B 커머스 상품 검수, 소비자 안전 안내, 회수·부적합 이력 확인에 사용합니다.
본 스킬은 NomaDamas k-skill의
mfds-drug-safety+mfds-food-safety(MIT)를 통합 정리했습니다.
Mandatory interview first — red flag 우선
증상·복용/섭취 상황이 언급되면 결론을 말하기 전에 반드시 먼저 되묻습니다.
권장 첫 질문:
- 누가 (본인/아이/임산부/고령자), 무엇을 언제 얼마나, 같이 먹은 음식·술·약, 현재 증상, 기저질환·알레르기
- red flag:
호흡곤란,의식저하,입술·혀 붓기,심한 발진,혈변,심한 탈수,심한 복통/고열,지속되는 구토/흉통
red flag 가 하나라도 있으면 API 조회보다 즉시 119·응급실·의료진 연결을 우선 안내합니다.
When to use
의약품:
- "이 약이랑 이 약 같이 먹어도 되니?"
- "타이레놀 먹는 중인데 판콜 같이 먹어도 돼?"
- "두드러기가 있는데 이 약 계속 먹어도 되나?"
- 식약처 공식 약 정보로 효능·주의사항 확인
식품:
- "이 음식 먹어도 괜찮니?" → 건강기능식품 원료 인정현황 + 검사부적합
- "차전자피 1일 섭취량 알려줘" → 기능성 원료 인정현황
- "이 김밥 먹고 배 아픈데 회수 이력 있어?" → 회수·부적합 목록
- 헬스/F&B 커머스에서 신상품 안전성 확인
When not to use
- 진단·처방·복용 지시
- 식중독 진단, 섭취 허가/금지 최종 판정
- red flag 또는 고위험군의 응급 상황 (의료진 우선)
Prerequisites
사용자 측 필수 시크릿 없음. 인터넷 연결만 있으면 동작합니다.
KSKILL_PROXY_BASE_URL(선택): self-host 프록시 사용 시. 비우면 기본 hostedhttps://k-skill-proxy.nomadamas.org사용.- 운영 측:
DATA_GO_KR_API_KEY(의약품 + 부적합),FOODSAFETYKOREA_API_KEY(건강기능식품 + 회수 live) — 프록시 서버에만 둡니다 FOODSAFETYKOREA_API_KEY발급:https://www.foodsafetykorea.go.kr회원가입 → OpenAPI 이용신청. 키 1개로 I-0040, I-0050, I0030, I0490, I2620 모두 사용
Workflow
A. 의약품 안전 체크
- 증상/복용 상황이 있으면 인터뷰 먼저.
- red flag 하나라도 있으면 즉시 응급 안내로 전환.
- 약 이름이 확인되면
/v1/mfds/drug-safety/lookup으로 e약은요·안전상비의약품 조회. - 효능·사용법·주의사항·상호작용·이상반응·보관법을 짧게 정리.
- "같이 먹어도 되나?"는 공식 상호작용 문구만 근거. 최종 판단은 약사·의료진.
B. 식품 안전 체크
- 증상/섭취 상황이 있으면 인터뷰 먼저.
- red flag → 즉시 응급 안내.
- "이거 먹어도 되나?" 흐름:
/v1/mfds/food-safety/product-report→ 건강기능식품 품목제조 신고사항(원재료·기능성·섭취 주의·기준규격, 고시형 원료 포함)/v1/mfds/food-safety/health-food-ingredient→ 기능성 원료 인정현황(개별인정형 1일 섭취량·주의사항)/v1/mfds/food-safety/inspection-fail→ 국내 검사부적합 이력/v1/mfds/food-safety/search→ 회수·부적합 공개 목록
- 제품명·업체명·기능성·섭취량·주의사항·부적합 사유를 짧게 정리. 먹어도 되는지 단정하지 않습니다.
- 프록시가
FOODSAFETYKOREA_API_KEY없이 동작하면 결과가 sample feed 기반일 수 있음을 warnings로 확인.
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 · 141 lines · 321 tokens per session scan A a9a830f31fbd
legal-mfds-safety is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 321 tokens to every session and 2,368 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…
email-personalization
Write hyper-personalized cold email icebreakers for B2B leads using their company intelligence and LinkedIn data. Use this skill whenever the user says "write icebreakers", "personalize emails", "email personalization", "cold email first lines", "write opening lines", "personalize outreach", "create email openers", or…
marketing-os-research
Answer an open question the Marketing OS already wrote down, then promote it to a finding. Takes its queue from the OS itself: files with status open-question in Intelligence/research/, open questions and untested beliefs in Analytics/what-works.md, and ideas with no established pain. Fans out one agent per stream in…
youtube-brief
Create a detailed video brief for a new YouTube video through a structured, collaborative process. This is a STEP-BY-STEP, interactive process — never output a complete brief immediately. Each step requires suggestions, user decision, then progression to the next step. USE THIS SKILL WHEN: - User wants to plan a…
generate-visual
Generate on-screen visuals for Ben van Sprundel's YouTube videos using Higgsfield. Same brand system as the thumbnails (charcoal + coral, dot-grid, flat-stylized icons, bold uppercase text), but optimized for in-video slides shown during a tutorial. Use when the user says generate a visual, make a slide, on-screen…
process-interviewer
Relentless process interviewer that extracts a complete, unambiguous plan from the user's head before any building begins. Use when the user wants to plan a complex task, design a process, build a skill, create a workflow, scope a project, or says things like "I want to build", "let's plan", "help me think through"…