galpi-korean-law-mcp: Skill for Codex

.agents/skills/galpi-law/SKILL.md

galpi-law is a skill for Codex from uscaidev/galpi-korean-law-mcp. It costs 98 tokens per session (1,026 once invoked), scanned A, original, MIT.

A skill for setting up and using Galpi, a retrieval service for Korean statutes, local ordinances, administrative rules, legal interpretations, precedents, and historical provisions. It also supports citations from HWPX documents, a Korean word-processing format.

In plain words
What is it for?
Use it to install or diagnose Galpi, search Korean legal sources, retrieve provisions as of a chosen date, examine precedents, and produce HWPX-based citations.
Why use it?
It provides a defined process for configuring access, finding the correct legal material, and checking results against the source. It keeps the tool focused on retrieving evidence rather than making legal decisions.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is uscaidev/galpi-korean-law-mcp's own configuration. It tells Codex how to work on galpi-korean-law-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything galpi-korean-law-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to uscaidev/galpi-korean-law-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/uscaidev/galpi-korean-law-mcp/main/.agents/skills/galpi-law/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/uscaidev/galpi-korean-law-mcp

Made for: Codex.

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 galpi-law

README.md
[![agentmods](https://agentmods.dev/badge/skills/uscaidev/galpi-korean-law-mcp/galpi-law/github.svg)](https://agentmods.dev/skills/uscaidev/galpi-korean-law-mcp/galpi-law)
Your own site
<a href="https://agentmods.dev/skills/uscaidev/galpi-korean-law-mcp/galpi-law"><img src="https://agentmods.dev/badge/skills/uscaidev/galpi-korean-law-mcp/galpi-law/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 galpi-law

Your own site · 80×15
<a href="https://agentmods.dev/skills/uscaidev/galpi-korean-law-mcp/galpi-law"><img src="https://agentmods.dev/badge/skills/uscaidev/galpi-korean-law-mcp/galpi-law.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,026 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 $0.00098 $0.01026
Opus 5 $0.00049 $0.00513
Sonnet 5 $0.00020 $0.00205
Haiku 4.5 $0.00010 $0.00103

Measured 12d ago against content hash 3ec6894f7cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

galpi-law 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 12d 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.

.agents/skills/galpi-law/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Galpi Law

Use Galpi as a source-retrieval tool, not as a chatbot or final legal decision maker.

First-run decision

  1. Locate the Galpi repository. If the user supplied only a GitHub URL, clone it to a persistent folder and run npm run setup from that folder.
  2. Run node scripts/galpi.mjs doctor --json before assuming setup is complete.
  3. If OC is missing, ask whether the user already has a Law Open API OC.
  4. If they do not, run npm run guide and direct them through onboarding/README.md. Do not invent an OC or claim approval succeeded.
  5. If they do, run npm run setup. Let the installer validate the four required list/detail targets and the optional precedent target, then register available local clients.
  6. When a required file is absent, use the matching sample in examples/mcp and explain where it belongs.

Read references/clients.md when connecting a client. Read references/api-contract.md when diagnosing identifiers or API responses.

Retrieval workflow

  1. Call korean_law_search with one target and a focused query. Continue automatically only for resolution.status exact, alias, or similar; stop and present candidates for ambiguous.
  2. Use only the returned id for detail tools. Never substitute 자치법규ID for the ordinance serial number or 안건번호 for an interpretation ID.
  3. Prefer korean_law_get_provision for a cited article, branch article, paragraph, item, or subitem. Do not scan a truncated full body to decide that a provision is absent.
  4. Use korean_law_search_precedent for a case number. Treat official-DB not_found with partial coverage as unconfirmed, not nonexistent.
  5. Use korean_law_get_at_date when contract date, disposition date, amendment date, transitional provisions, or retroactivity matter.
  6. Use korean_law_extract_citations for text or HWPX. Verify each extracted citation separately; contentMatch=not_assessed is not a legal-match finding.
  7. Use korean_law_compare_provision_versions for a generated two-date comparison and label it separately from an official new-old table. Use korean_law_get_transitional_provisions before deciding temporal applicability.
  8. Use korean_law_check_access when authorization or endpoint coverage is uncertain.
  9. Report title, exact provision, source URL, source ID, effective date, retrieval time, verification status, provenance, and coverage. Tell the user to confirm the official original before a final decision.

Read the full file on GitHub · 58 lines

Files

What ships with it

3 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.

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. 12d ago First seen · 58 lines · 98 tokens per session scan A 3ec6894f7cd4

Subscribe to this mod's changes

galpi-law is a skill published in the GitHub repository uscaidev/galpi-korean-law-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,026 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 2026-08-31.

Related

Other skills, from other repositories

korean-privacy-terms

A skill package for creating privacy policies and terms of service for South Korea, the European Union, the United States, or combined Korean and EU use. It covers South Korea's PIPA, the EU's GDPR, and US CCPA/CPRA requirements.

kimlawtech/korean-privacy-terms · 86 tokens

privacy-us

A guided tool for creating a US privacy policy based on the California CCPA/CPRA and several other state privacy laws. It asks about the service, the data collected, service providers, dates, and design preferences.

kimlawtech/korean-privacy-terms · 101 tokens

privacy-global-jp

A document generator for Korean services that also serve people in Japan. It creates Korean and Japanese privacy policies and terms of service while reflecting relevant rules in both countries.

kimlawtech/korean-privacy-terms · 71 tokens

privacy-global

A document-generation tool for creating privacy policies and terms of service for a Korean company serving users in both Korea and the European Union. It produces Korean documents based on Korean privacy rules and English documents based on EU rules such as the GDPR, the European data-protection law.

kimlawtech/korean-privacy-terms · 68 tokens

privacy-eu

A generator for privacy notices, terms of service, consent windows, and cookie banners for services aimed at people in the European Union. It covers GDPR and several related EU consumer and digital-service rules.

kimlawtech/korean-privacy-terms · 70 tokens

privacy-jp

A Japanese-language document generator for services built with Next.js. It creates privacy policies, terms of service, consent dialogs, and cookie banners while considering Japan's personal-information and consumer-protection laws.

kimlawtech/korean-privacy-terms · 74 tokens