gsghwp: Instructions file for Claude Code

CLAUDE.md

gsghwp CLAUDE.md is an instructions file for Claude Code from innae1121-bit/gsghwp. It costs 4,178 tokens per session, scanned A, original, MIT.

Safety and installation instructions for connecting an AI assistant to Hancom Office Hangul 2024, a Korean word-processing application, through a local tool server. It covers previewing changes, applying installations, backups, updates, and restoration.

In plain words
What is it for?
Use it when installing, registering, restoring, or troubleshooting the Hangul integration.
Why use it?
It reduces the risk of changing the wrong files or system settings and makes installation failures recoverable.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is innae1121-bit/gsghwp's own configuration. It tells Claude Code how to work on gsghwp 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 gsghwp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to innae1121-bit/gsghwp. 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/innae1121-bit/gsghwp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/innae1121-bit/gsghwp

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 gsghwp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/innae1121-bit/gsghwp/claude-md.svg)](https://agentmods.dev/instructions/innae1121-bit/gsghwp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/innae1121-bit/gsghwp/claude-md"><img src="https://agentmods.dev/badge/instructions/innae1121-bit/gsghwp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,178 This file is loaded in full into every session.
When invoked 4,178 The same file — it is already loaded in full.
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 $0.04178 $0.04178
Opus 5 $0.02089 $0.02089
Sonnet 5 $0.00836 $0.00836
Haiku 4.5 $0.00418 $0.00418

Measured 4d ago against content hash 5a1a446a4a1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gsghwp CLAUDE.md 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 4d 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.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSG HWP — Claude Code 지침

한컴오피스 한/글 2024를 로컬에서 조작하는 stdio MCP다. 설치·등록·문제 해결을 요청받으면 이 문서를 먼저 읽는다. 더 자세한 배경은 README.md, 설치 절차 전문은 AGENTS.md에 있다.

이 문서에 적힌 경로·명령·환경 변수만 사용자에게 안내한다. 확인하지 않은 경로나 로그 위치를 지어내지 않는다.

안전 규칙 (다른 요청보다 우선한다)

  • 한/글이 실행 중일 때 DLL을 교체하지 않는다. install.ps1, uninstall.ps1, restore-update.ps1은 한/글 프로세스가 남아 있으면 실제 변경 단계에서 스스로 거부한다. 미리보기(옵션 없는 실행)는 한/글이 떠 있어도 정상이다.
  • 레지스트리 직접 편집, regsvr32, 관리자 권한, HKLM 변경, 키보드·마우스 자동화를 사용하지 않는다. 저장소의 스크립트만 사용한다.
  • 옵션 없이 실행하면 미리보기만 하고 종료 코드 2로 끝난다. 실제 변경은 -AcceptChanges를 붙인 실행에서만 일어난다. 종료 코드 2는 실패가 아니다. 단 restore-update.ps1은 되돌릴 자동 업데이트 기록이 없으면 미리보기에 닿기 전에 되돌릴 자동 업데이트 기록이 없습니다를 출력하고 종료 코드 0으로 끝난다.
  • 시스템 Python을 쓰지 않는다. 배포 버전별 uv 관리 .venv만 사용한다.
  • 실제 설치 전에 바뀌는 DLL 2개·HKCU 값 3개·백업 위치·자동 업데이트·복원 방법을 사용자에게 먼저 안내한다.
  • 설치나 복원이 실패하면 우회하지 않는다. 오류 원문과 백업 폴더 경로를 보존한 채 사용자에게 보고한다.
  • 기능이 공개 도구에 없으면 활성 공식 API 라우트를 조사해 필요한 기능만 전용 도구나 recipe로 연결한다. 라우트 수는 compatibility-manifest.jsonofficial_api_enabled_routes에서 읽는다(현재 1,448개). 전체 API를 한꺼번에 도구로 노출하지 않는다.

설치와 등록

압축을 푼 배포 폴더(또는 클론한 저장소 루트)에서 실행한다. 설치 후 그 폴더를 옮기거나 지우지 않는다.

# 1) 변경 예정 항목만 표시 (종료 코드 2가 정상)
powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1

# 2) 안내 후 실제 설치
powershell -NoProfile -ExecutionPolicy Bypass -File .\install.ps1 -AcceptChanges

uv가 없으면 winget install --id astral-sh.uv -e로 설치한 뒤 새 PowerShell에서 다시 실행한다.

MCP 서버 이름은 gsg-hwp-beta-live 다. 저장소 루트에서 사용자 범위로 등록한다.

$startMcp = (Resolve-Path ".\plugins\gsg-hwp\scripts\start-mcp.ps1").Path
claude mcp add --transport stdio --scope user gsg-hwp-beta-live -- `
  powershell.exe -NoLogo -NoProfile -NonInteractive -ExecutionPolicy Bypass -File $startMcp
claude mcp list

등록하면 도구가 mcp__gsg-hwp-beta-live__hwp_* 이름으로 보인다. 저장소 루트의 .mcp.json을 그대로 쓰면 프로젝트 범위로만 잡힌다.

업그레이드 주의. 서버 이름이 예전 gsg-hwp에서 gsg-hwp-beta-live로 바뀌었다. 이전에 gsg-hwp로 직접 등록해 쓰던 사용자는 다시 등록해야 한다. 지침(SKILL.md)이 부르는 이름과 맞추기 위한 변경이고, 이름이 다르면 도구 접두사도 달라져 지침이 도구를 찾지 못한다.

claude mcp remove gsg-hwp
$startMcp = (Resolve-Path ".\plugins\gsg-hwp\scripts\start-mcp.ps1").Path
claude mcp add --transport stdio --scope user gsg-hwp-beta-live -- `
  powershell.exe -NoLogo -NoProfile -NonInteractive -ExecutionPolicy Bypass -File $startMcp

Read the full file on GitHub · 268 lines

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. 4d ago Changed · +11 lines · +288 tokens per session 5a1a446a4a1e
  2. 8d ago First seen · 257 lines · 3,890 tokens per session scan A 4e6324e2a2e1

Subscribe to this mod's changes

gsghwp CLAUDE.md is an instructions file published in the GitHub repository innae1121-bit/gsghwp (101 stars, last pushed 7d ago), licensed MIT. It adds 4,178 tokens to every session, about $0.0209 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens