agentmods.dev

velog_mcp AGENTS.md

velog_mcp AGENTS.md is an instructions file for Codex, OpenCode from seongwon030/velog_mcp. It costs 1,560 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for a Node.js and TypeScript MCP server that lets an agent draft, publish, edit, delete, and manage content on Velog, a Korean blogging platform.

In plain words
What is it for?
It is for working on Velog posts, drafts, comments, tags, series, uploads, RSS, notifications, and related API tools while following the repository's conventions.
Why use it?
It explains the project's structure, build and lint commands, authentication needs, and the need to review actions that publish or delete public content.

Instructions file for CodexOpenCode

not rated 5 6d ago A scan 1,560 tokens original MIT
View the source file seongwon030/velog_mcp npmjs.com
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.

agentmods
npx agentmods add instructions/seongwon030/velog_mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/seongwon030/velog_mcp

Made for: Codex, OpenCode.

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 velog_mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seongwon030/velog_mcp/agents-md.svg)](https://agentmods.dev/instructions/seongwon030/velog_mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/seongwon030/velog_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/seongwon030/velog_mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,560 This file is loaded in full into every session.
When invoked 1,560 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01560 $0.01560
Opus 5 $0.00780 $0.00780
Sonnet 5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured 5d ago against content hash 17c5daf4300d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

velog_mcp AGENTS.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 5d 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.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

프로젝트 개요

velog-mcp-claude는 Claude가 Velog 콘텐츠를 초안 작성, 발행, 수정, 삭제, 조회할 수 있게 해주는 Node.js 18+ 기반 MCP 서버입니다. Velog의 비공개 GraphQL 및 REST API를 사용합니다.

이 프로젝트는 리버스 엔지니어링 기반의 비공식 연동입니다. Velog API 동작은 언제든 바뀔 수 있다고 보고, 발행이나 삭제처럼 되돌리기 어렵거나 공개 범위에 영향을 주는 작업은 반드시 사용자의 검토를 거치세요.

스택과 명령어

  • 런타임: Node.js 18+, ESM ("type": "module").
  • 언어: TypeScript, strict 활성화, NodeNext 모듈 해석.
  • 원본 소스: src/.
  • 빌드 결과물: dist/; 생성된 파일을 직접 수정하지 마세요.
  • 포맷/린트: Biome, 공백 2칸 들여쓰기, 큰따옴표.

저장소 루트에서 다음 명령을 사용하세요.

npm run build      # TypeScript를 dist/로 컴파일
npm run lint       # Biome 검사
npm run lint:fix   # Biome 자동 수정 및 import 정리
npm run health     # 실제 Velog API 스모크 테스트; ~/.velog-mcp.json 필요
npm run dev        # tsc --watch
npm start          # dist/index.js 실행
npm run setup      # dist/setup.js 실행

TypeScript를 변경한 뒤에는 npm run build를 실행하세요. Biome 검사 대상인 소스나 문서를 변경했다면 npm run lint를 실행하세요. npm run health는 실제 Velog 토큰 접근이 필요하다고 명확히 판단될 때만 실행하세요.

아키텍처

  • src/index.ts는 MCP 툴 스키마를 정의하고 툴 호출을 라우팅합니다.
  • src/tools/index.ts는 개별 툴 구현을 다시 export합니다.
  • src/tools/*.ts는 포스트, 초안, 댓글, 좋아요, 검색, 트렌딩, 알림, 읽을 목록, RSS, 시리즈, 태그, 임시저장, 업로드, GitHub 가져오기 등 기능 영역별 구현을 담습니다.
  • src/auth.ts는 Velog 토큰 로드, Set-Cookie 기반 토큰 갱신, 공용 GraphQL 래퍼를 담당합니다.
  • src/setup.ts는 설정 CLI 진입점입니다.
  • scripts/health-check.mjs는 실제 인증/읽기/트렌딩/쓰기-삭제 검사를 수행합니다.
  • docs/overview.md, docs/security.md, docs/roadmap.md에는 로컬 아키텍처, 안전 주의사항, 기능 방향이 정리되어 있습니다.

새 MCP 툴을 추가할 때는 관련 위치를 모두 갱신하세요.

  1. src/tools/<name>.ts에 툴을 구현합니다.
  2. src/tools/index.ts에서 export합니다.
  3. src/index.ts의 ListToolsRequestSchema에 툴 스키마를 추가합니다.
  4. CallToolRequestSchema의 switch 문에 Zod 검증과 호출 분기를 추가합니다.
  5. 사용자에게 노출되는 동작이 바뀌면 README.md와 관련 문서를 갱신합니다.

API와 동작 메모

  • Velog GraphQL 엔드포인트: https://v2.velog.io/graphql.
  • 이미지 업로드 엔드포인트: https://v3.velog.io/api/files/v3/upload.
  • 트렌딩 데이터는 https://cache.velcdn.com에서 가져옵니다.
  • GraphQL 요청에는 유효한 operationName을 포함하세요. 일부 mutation은 이것이 없으면 실패하거나 null을 반환합니다.
  • 작성/수정 mutation에서는 기존 코드가 명시적으로 null을 전달하는 필드를 유지하세요. 특히 thumbnail, series_id, token에 주의하세요.
  • 초안은 프로세스 메모리에만 저장됩니다(src/tools/draft.ts). MCP 서버를 재시작하면 발행하지 않은 초안은 사라집니다.

Read the full file on GitHub · 111 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. 5d ago First seen · 111 lines · 1,560 tokens per session scan A 17c5daf4300d

Subscribe to this mod's changes

velog_mcp AGENTS.md is an instructions file published in the GitHub repository seongwon030/velog_mcp (5 stars, last pushed 6d ago), licensed MIT. It adds 1,560 tokens to every session, about $0.0078 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.

Writing and docsblogclaudecodexmcpmodel-context-protocol
Related

Other instructions, from other repositories

violet AGENTS.md

AGENTS.md instructions for VOD-Studio/violet, covering violet (blog-project), 架构与代码边界, 架构耦合约束, 开发流与命令 (makefile) and 后端 (api/) 须知.

VOD-Studio/violet · 6,509 tokens

basic-blog AGENTS.md

Instructions for daocodotorg/basic-blog, covering agent notes — basic-blog monorepo, scope, npm release (automatic when version changes), when to tag and commands (agent should run these unless the user opts out).

daocodotorg/basic-blog · 618 tokens

openrouter-mcp-multimodal AGENTS.md

AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 793 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

seekstone CLAUDE.md

Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.

shaqmughal/seekstone · 1,116 tokens

Plonk AGENTS.md

AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens