blog-posting-auto: Instructions file for Claude Code

CLAUDE.md

blog-posting-auto CLAUDE.md is an instructions file for Claude Code from unclejobs-ai/blog-posting-auto. It costs 1,878 tokens per session, scanned A, original, MIT.

A Korean-language blog publishing workflow that moves from research through fact-checking, planning, writing, review, and publication to a Notion database.

In plain words
What is it for?
Use it to turn a topic or keyword into a reviewed Korean blog post published in Notion.
Why use it?
It separates unsupported or mistaken information before later stages use it, while keeping each run's research, draft, and review files organized.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code; runs codex exec.

This is unclejobs-ai/blog-posting-auto's own configuration. It tells Claude Code how to work on blog-posting-auto 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 blog-posting-auto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unclejobs-ai/blog-posting-auto. 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/unclejobs-ai/blog-posting-auto/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/unclejobs-ai/blog-posting-auto

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 blog-posting-auto CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/unclejobs-ai/blog-posting-auto/claude-md"><img src="https://agentmods.dev/badge/instructions/unclejobs-ai/blog-posting-auto/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,878 This file is loaded in full into every session.
When invoked 1,878 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 $0.01878 $0.01878
Opus 5.5 $0.00751 $0.00751
Sonnet 5.5 $0.00376 $0.00376
Haiku 4.5 $0.00188 $0.00188

Measured 10d ago against content hash f697e71cf8fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blog-posting-auto 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

blog-posting-auto

Claude Code 기반 한국어 블로그 글 자동화 파이프라인. Researcher → Fact-Checker → Planner → Writer → Reviewer → (Image Router → Image Generator, 선택) → Publisher 서브에이전트가 /blog-pipeline 스킬을 통해 직렬 실행, 최종 결과를 Notion DB에 발행. Fact-Checker가 환각·오인용을 격리해 downstream을 깨끗하게 유지.

실행 흐름

user: /blog-pipeline <주제 또는 키워드>
  └─ Opus Orchestrator (메인 세션)
      ├─ 1.  blog-researcher    → workspace/{run_id}/research.md
      ├─ 1.5 blog-fact-checker  → workspace/{run_id}/research.verified.md
      │                          + research.rejected.md  (탈락 audit)
      ├─ 2.  blog-planner       → workspace/{run_id}/plan.md
      ├─ 3.  blog-writer        → workspace/{run_id}/draft.md
      ├─ 4.  blog-reviewer      → workspace/{run_id}/final.md
      ├─ 4.5 blog-image-router  → workspace/{run_id}/image-prompts.json   (선택)
      ├─ 4.6 scripts/codex-images.sh generate
      │                          → workspace/{run_id}/images/*.png
      │                          + images.manifest.json  (codex exec, 선택)
      └─ 5.  blog-publisher     → Notion page URL (meta.json 저장)

디렉토리

  • .claude/agents/ — 7개 서브에이전트 정의 (researcher / fact-checker / planner / writer / reviewer / image-router / publisher)
  • scripts/codex-images.sh: 4.6단계 이미지 생성 (generate) + placeholder 교체 사본 (swap)
  • .claude/skills/blog-pipeline/ — /blog-pipeline 슬래시 스킬 진입점
  • .claude/style/ — 톤·금지표현·체크리스트 (모든 에이전트가 SessionStart hook으로 로드)
  • .claude/hooks/ — SessionStart / UserPromptSubmit / PreToolUse / SubagentStop / Stop 자동 체크포인트 (날짜 주입 + 금지표현 차단)
  • workspace/{run_id}/ — 실행별 산출물 (gitignored)
  • examples/ — 참고 글 샘플 (스타일 학습용)

발행 타겟

/blog-pipeline publisher는 .env에 설정한 Notion DB로 발행한다. 사용자가 명시적으로 다른 곳을 지정하지 않는 한 .env 값을 사용.

  • Parent page: .env의 NOTION_PARENT_PAGE_ID (Notion 페이지 URL 끝 32자 hex)
  • DB: .env의 NOTION_DATABASE_ID (inline DB URL 끝 32자 hex)
  • Title field: .env의 NOTION_DB_TITLE_FIELD (DB 스키마의 title 속성명, 기본 이름)

Notion DB ID 찾기: Notion에서 DB 우상단 ... → Copy link → URL의 마지막 32자 hex가 DB ID.

Read the full file on GitHub · 99 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 Changed · +18 lines · +543 tokens per session f697e71cf8fc
  2. 2mo ago First seen · 81 lines · 1,335 tokens per session scan A 4348f870fb27

Subscribe to this mod's changes

blog-posting-auto CLAUDE.md is an instructions file published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 6d ago), licensed MIT. It adds 1,878 tokens to every session, about $0.0075 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 2026-08-30.

Related

blog-posting-auto CLAUDE.md compared with instructions from other repositories

blog-posting-auto CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
blog-posting-auto CLAUDE.mdunclejobs-ai/blog-posting-autoInstructions file426d agoMITA1,878Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode