agentmods.dev

naver-blog-mcp: Instructions file for Claude Code

CLAUDE.md

naver-blog-mcp CLAUDE.md is an instructions file for Claude Code from jjorae/naver-blog-mcp. It costs 6,080 tokens per session, scanned A, original, MIT.

A set of instructions for developing and using an MCP server that creates formatted Naver Blog posts with images through a browser.

In plain words
What is it for?
Saving drafts, publishing only after explicit confirmation, pasting formatted content, uploading local images up to 10 MB, and representing files, formulas, or places in post content.
Why use it?
It records design decisions that reduce accidental publishing, protect login details, and handle Naver's changing page controls.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jjorae/naver-blog-mcp's own configuration. It tells Claude Code how to work on naver-blog-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 naver-blog-mcp configures →

not rated 0repo 15d ago A scan 6,080 tokens original MIT
View source ↗ jjorae/naver-blog-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to jjorae/naver-blog-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/jjorae/naver-blog-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jjorae/naver-blog-mcp

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 naver-blog-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jjorae/naver-blog-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jjorae/naver-blog-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jjorae/naver-blog-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jjorae/naver-blog-mcp/claude-md/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 naver-blog-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jjorae/naver-blog-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jjorae/naver-blog-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,080 This file is loaded in full into every session.
When invoked 6,080 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 $0.06080 $0.06080
Opus 5 $0.03040 $0.03040
Sonnet 5 $0.01216 $0.01216
Haiku 4.5 $0.00608 $0.00608

Measured 10d ago against content hash df7cf6dbfbc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

naver-blog-mcp 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 10d 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 · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

네이버 블로그에 서식·이미지 포함 글을 작성하는 MCP 서버. Playwright 기반.

지켜야 할 설계 결정

이 결정들은 이유가 있어서 내린 것이다. 바꾸려면 먼저 물어볼 것.

  1. 비밀번호를 저장하지 않는다. login_setup.py로 사람이 직접 로그인해 playwright-state/storage_state.json에 쿠키만 덤프한다. 서버는 그 파일만 읽는다. CAPTCHA·2차인증은 사람이 처리한다. 로그인 자동화 코드를 추가하지 말 것 — 봇 탐지에 걸리는 표면이자 계정 제재 리스크다.

  2. 셀렉터는 selectors.py에만 둔다. 다른 파일에 셀렉터 문자열을 하드코딩하지 말 것. 각 항목은 후보 리스트이고 S.first()가 위에서부터 시도한다. 후보 순서는 의미 기반(role/aria-label/텍스트) → 클래스 기반. 네이버 클래스명은 난독화돼 자주 바뀐다.

  3. 기본값은 임시저장. create_draft는 발행하지 않는다. publish_draft(confirm=True)가 별도다. 셀렉터가 깨졌을 때 라이브 블로그에 깨진 글이 올라가는 것보다 임시저장함에 쌓이는 게 낫다.

  4. 본문 입력은 클립보드 HTML 붙여넣기가 1차 경로. 스마트에디터 ONE은 HTML 편집 모드가 없지만 리치 텍스트 붙여넣기는 받는다. 툴바 클릭보다 훨씬 안정적이다. 실패 시 키보드 단축키 폴백(type_spans). 툴바 클릭은 최후수단.

  5. 이미지는 붙여넣기 불가. 툴바 이미지 버튼 → expect_file_chooser 가로채기만 가능하다. 그래서 ir.segment()가 본문을 [html | image | html]로 쪼갠다. 로컬 경로만, 10MB 제한.

  6. 마크다운에 없는 블록은 :::name 인자::: 디렉티브로 쓴다. :::file 로컬경로::: / :::formula x^2+y^2=z^2::: / :::place 강남역:::. 일정 등도 같은 틀에 얹는다. 이유: 링크 문법([라벨](경로))을 재사용하면 진짜 링크와 구분이 모호해 오탐이 난다. 디렉티브는 표준 마크다운 뷰어에서 그냥 텍스트로 보여 원문이 깨지지 않는다. 모르는 디렉티브는 버리지 않고 문단으로 강등한다.

현재 상태

2026-08-25 실측 완료. check_session / list_categories / create_draft E2E 통과.

  • ir.py — 검증 완료. Segment 에 blocks 필드 추가(폴백이 세그먼트 단위로 동작하게).
  • session.py, login_setup.py — 동작 확인.
  • selectors.py — 8개 항목 전부 실측 확정. 모두 1순위 후보로 잡힌다. 후보 순서 원칙이 바뀌었다 (파일 상단 주석 참조): 네이버의 data-click-area / data-testid / data-name / data-a11y-title 가 가장 오래 간다. 텍스트 매칭은 마지막에, 그것도 컨테이너로 스코프를 좁힌 뒤에만.
  • editor.py — 발행 레이어 헬퍼 추가. macOS 단축키(ControlOrMeta) 반영.
  • server.py — mcp 2.0 (MCPServer) 기준. 툴 6개: check_session / list_categories / list_drafts / create_draft / delete_draft / publish_draft / delete_post.

고친 것

  1. dismiss_popups 가 매 실행마다 본문 취소선을 켜고 있었다. 스코프 없는 button:has-text('취소') 가 툴바의 취소선 버튼을 부분매칭했다. (취소선 상태 False→True 로 확인) → RECOVER_POPUP_CANCEL 을 .se-popup 안으로 한정.
  2. networkidle 로 기다리면 TargetClosedError 가 난다. 네이버 에디터는 연결을 계속 열어둬서 idle 에 도달하지 않는다 → goto_editor() 가 domcontentloaded + 에디터 iframe 명시적 대기를 쓴다.
  3. 카테고리/태그는 발행 설정 레이어 안에만 존재한다. 레이어를 열지 않던 list_categories / create_draft(tags=...) 가 조용히 실패하고 있었다.
  4. check_session 이 LOGGED_IN_MARK 로 판정했는데 그 마크는 로그인 상태에서도 visible=False 다 → MYBLOG_PROBE_URL 리다이렉트 판정으로 교체.

Read the full file on GitHub · 298 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. 10d ago First seen · 298 lines · 6,080 tokens per session scan A df7cf6dbfbc1

Subscribe to this mod's changes

naver-blog-mcp CLAUDE.md is an instructions file published in the GitHub repository jjorae/naver-blog-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 6,080 tokens to every session, about $0.0304 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 instructions, from other repositories

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

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

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

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