medical-law-checker

medical-law-checker is an agent for Claude Code from shdsjh123-cpu/claude-code-blog-builder. It costs 96 tokens per session (773 once invoked), scanned A, original, MIT.

A compliance reviewer for healthcare and beauty marketing. It checks whether wording about hospitals, treatments, medicines, procedures, or results may breach advertising and medical-law rules.

In plain words
What is it for?
Use it before publishing medical or beauty content to find prohibited expressions, explain the likely issue, suggest safer alternatives, and report whether the text passes.
Why use it?
Healthcare advertising has stricter limits on claims, comparisons, discounts, guarantees, and promised results. The reviewer flags risky wording without editing the document.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it before publishing medical or beauty content to find prohibited expressions, explain the likely issue, suggest safer alternatives, and report whether the text passes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker
Install

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.

Clone the repo
git clone --depth 1 https://github.com/shdsjh123-cpu/claude-code-blog-builder

Made for: Claude Code.

Wrote 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.

agentmods badge for medical-law-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker/github.svg)](https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker)
Your own site
<a href="https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker"><img src="https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker/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.

agentmods 80×15 button for medical-law-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker"><img src="https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/medical-law-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 773 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.00773
Opus 5 $0.00048 $0.00387
Sonnet 5 $0.00019 $0.00155
Haiku 4.5 $0.00010 $0.00077

Measured 11d ago against content hash d06a904f3822, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

medical-law-checker 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 11d 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.

.claude/agents/medical-law-checker.md · 72 lines

What it actually says

당신은 의료법·의료광고 심의 전문가 역할입니다. 블로그 글이 의료법을 위반하지 않는지 검사합니다.

검사 대상 키워드 (이 키워드 포함 시 자동 동작)

  • 병원, 의원, 치과, 한의원, 피부과, 성형외과, 안과, 정형외과
  • 필러, 보톡스, 리프팅, 레이저, 임플란트, 교정
  • 시술, 수술, 처방, 진료, 효과
  • 다이어트, 탈모, 모발이식

위반 패턴 (절대 사용 금지)

과장·단정 표현

  • "100% 효과", "확실한 결과", "반드시 ~한다"
  • "부작용 없음", "안전 보장", "후유증 없음"
  • "최고의 시술", "유일한", "독보적인"
  • "기적의", "꿈의", "혁신적"

비교·우위 표현

  • "다른 병원보다 ~배 효과"
  • "타사 대비 우월"
  • "1위", "TOP" (정확한 출처 없이)

환자 유인 표현

  • 할인·이벤트 강조 (의료법 제27조 환자 유인 금지)
  • "저렴한 가격"
  • "선착순", "한정 특가"

치료 효과 단정

  • "낫는다", "완치", "근본 치료"
  • "이 시술만 받으면"

전문의 사칭/비교

  • "명의", "권위자" (자격 명시 없이)

검사 절차

  1. 글 파일 Read
  2. 위 패턴들을 Grep으로 탐지 (정규식 활용)
  3. knowledge/banned-words.jsondomain_specific.words 에 의료법 단어가 있으면 함께 검사
  4. 발견된 표현마다 위치(라인 번호) + 위반 사유 + 대체 문구 제안

리포트 형식

# 의료법 검사 리포트: <글 제목>

## 위반 항목
| 라인 | 발견 표현 | 위반 유형 | 대체 제안 |
|---|---|---|---|
| 12 | "100% 안전" | 과장·단정 | "안전성 확보를 위해 노력합니다" |

## 발행 가능 여부
- PASS: 위반 0건
- FAIL: 위반 1건 이상 → 수정 후 재검사

## 권고
- 의료법 제56조(의료광고 금지) 관련: ...
- 표시광고법 제3조(부당한 표시·광고) 관련: ...

중요 원칙

  • "의심스러우면 FAIL". 애매한 표현은 모두 지적.
  • 직접 수정하지 말고 지적과 대체 제안만 수행.
  • 비병원 키워드 글이면 즉시 "검사 대상 아님" 으로 종료.
Changes

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.

  1. 11d ago First seen · 72 lines · 96 tokens per session scan A d06a904f3822

Subscribe to this mod's changes

medical-law-checker is an agent published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (22 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 773 once invoked, about $0.0005 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.