agentmods.dev

legal-law-research

legal-law-research is a skill for Claude Code from modu-ai/moai-cowork. It costs 44 tokens per session (781 once invoked), scanned A, original, Apache-2.0.

A legal research tool for finding and checking South Korean laws, court decisions, administrative rules, local ordinances, treaties, and official interpretations. It can also verify whether cited provisions or decisions exist and are still applicable.

In plain words
What is it for?
Use it to retrieve statute text, search decisions, verify citations, check which law applied at a past date, compare old and new provisions, and trace how rules affect one another.
Why use it?
It helps reduce mistakes caused by outdated or incorrect legal references by checking official source text and historical applicability. It is an AI-assisted research aid, not legal advice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the moai-lawyer plugin — 13 skills, 2 agents shipped together

not rated 315repo +1 changed 1mo ago A scan SkillSpector: warn 44 tokens original Apache-2.0

Good fit Use it to retrieve statute text, search decisions, verify citations, check which law applied at a past date, compare old and new provisions, and trace how rules affect one another.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/legal-law-research
View source ↗ modu-ai/moai-cowork cowork.mo.ai.kr
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.

Any agent
npx skills add modu-ai/moai-cowork --skill legal-law-research
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-lawyer, the plugin that ships this one along with the rest of its 13 skills, 2 agents.

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 legal-law-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/legal-law-research/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/legal-law-research)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/legal-law-research"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/legal-law-research/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 legal-law-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/legal-law-research"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/legal-law-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 781 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 74
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
  • high Agent Snooping · line 83
    Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.
    Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
  • high Privilege Escalation · line 89
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00044 $0.00781
Opus 5.5 $0.00018 $0.00312
Sonnet 5.5 $0.00009 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 1mo ago against content hash aacab76cbe0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

legal-law-research 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 1mo 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.

plugins/moai-lawyer/skills/legal-law-research/SKILL.md · 35 lines

What it actually says

법령 리서치

법률 자문이 아닌 참고 자료다. 법령의 존재, 사건 날짜에 적용되는 판본, 판례의 내용과 이후 변경 여부를 각각 확인한다.

조회 경로

  1. 현재 호스트에서 korean-law MCP의 실제 도구 목록과 연결 상태를 확인한다. 보이면 사용 가능한 search_law, get_law_text, legal_analysis 등의 현재 스키마를 읽고 필요한 도구만 호출한다. 과거 문서의 도구 수·매개변수를 현재 계약으로 단정하지 않는다.
  2. 도구가 없거나 인증되지 않았다면 국가법령정보센터와 해당 주무 기관의 공식 웹페이지를 직접 조회한다. MCP가 없다는 이유로 법령 조사를 포기하지 않는다. 웹 조사와 MCP 검증은 보고서에 구분해 쓴다.
  3. 법제처 Open API 안내는 OC 인증값을 요구한다. 키가 필요하면 공식 신청 경로를 안내하고 앱의 검증된 보안 설정 방법을 사용한다. 키를 채팅에 입력받거나 작업 파일·보고서·URL 예시에 실제 값으로 기록하지 않는다. Codex는 Claude user_config를 자동 치환하지 않으므로 연결 방식을 확인하지 않은 채 성공을 약속하지 않는다. TLS 인증서 오류가 나도 검증을 끄거나 HTTP로 낮추지 않는다.

확인 순서

  • 법령명, 조·항·호, 시행일, 사건 발생일과 관할을 정한다. 현행법과 과거 법령을 혼동하지 않는다.
  • 원문 조항과 부칙·경과규정, 관련 시행령·고시를 확인한다. 도구의 applicable_law 결과가 있더라도 원문과 적용 사실을 대조한다.
  • 판례는 사건번호·법원·선고일·판시 내용을 공식 기록으로 확인한다. cite_check가 있으면 후속 인용을 조사하되, 결과 하나만으로 판례가 법적으로 살아 있다고 단정하지 않는다.
  • 문서 속 인용은 verify_citations가 있으면 보조 검사를 하고, 모든 인용의 원문 링크를 개별 대조한다. 도구가 실패하거나 링크가 열리지 않으면 검증 공백으로 적는다.
  • 법령 개정 비교는 서로 다른 시행 판본의 실제 조문을 대조해 바뀐 문구를 인용 범위 내에서 요약한다.

출력

주장·인용 공식 원문 URL 판본·날짜 확인한 내용 해석·한계
조문 또는 판례 직접 연결 시행일·선고일 원문으로 확인한 사실 사건 적용은 별도 판단

질문의 결론을 내기 위한 사실이 없으면 필요한 사실을 적고 조건부로 설명한다. 법령 본문과 판례, 학설·행정해석, 자신의 추론을 구분한다. 변호사 검토가 필요한 쟁점과 실제 조회하지 못한 출처를 명시한다.

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. 1mo ago Changed · +1 lines aacab76cbe0f
  2. 1mo ago Changed · -153 lines · -322 tokens per session bbabb8f3df9d
  3. 2mo ago First seen · 187 lines · 366 tokens per session scan A 7b66002a317a

Subscribe to this mod's changes

legal-law-research is a skill published in the GitHub repository modu-ai/moai-cowork (315 stars, last pushed 28d ago), licensed Apache-2.0. It adds 44 tokens to every session and 781 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 2026-09-03.

Claude CodeLegal and complianceResearchai-agentsanthropicclaude-pluginsmarketplaceplugin-marketplace
Related

legal-law-research compared with skills from other repositories

legal-law-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
legal-law-researchmodu-ai/moai-coworkSkill31528d agoApache-2.0A44Claude Code
penalista-attiSynthos-Logic/penalista-italiaSkill114d agoMITA235Claude Code
penalista-cautelareSynthos-Logic/penalista-italiaSkill114d agoMITA196Claude Code
penalista-giurisprudenzaSynthos-Logic/penalista-italiaSkill114d agoMITA214Claude Code
penalista-esecuzioneSynthos-Logic/penalista-italiaSkill114d agoMITA223Claude Code
penalista-scadenzeSynthos-Logic/penalista-italiaSkill114d agoMITA194Claude Code
penalista-archivioSynthos-Logic/penalista-italiaSkill114d agoMITA228Claude Code