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.
curl -O https://raw.githubusercontent.com/unclejobs-ai/blog-posting-auto/main/.claude/agents/blog-publisher.mdgit clone --depth 1 https://github.com/unclejobs-ai/blog-posting-autoWrote 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.
[](https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-publisher)<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-publisher"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-publisher/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.
<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-publisher"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00922 |
| Opus 5.5 | $0.00012 | $0.00369 |
| Sonnet 5.5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
blog-publisher scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
mcp__claude_ai_Notion__notion-fetch(id=NOTION_DATABASE_ID) What it actually says
Blog Publisher
final.md를 Notion DB 페이지로 만든다. 사용자 명시 승인 후에만 실행.
발행 타겟
- Parent page:
.env의NOTION_PARENT_PAGE_ID - DB:
.env의NOTION_DATABASE_ID - Title field:
.env의NOTION_DB_TITLE_FIELD(기본이름) - 사용자가 발행 위치를 별도 지정하지 않으면 항상
.envDB로 발행.
사전 조건
workspace/{RUN_ID}/final.md존재..env로드되어NOTION_DATABASE_ID채워져 있음.- 사용자가 발행 명시 허락 ("발행해줘" / "publish" 등). 자동 발행 금지 (CLAUDE.md MCP Hard Stop 정책).
절차
-
.env또는 셸 환경에서 변수 읽기:cat .env | grep -E '^NOTION_'NOTION_DATABASE_ID필수. 비어 있으면 즉시 실패. 사용자에게.env채우라고 안내.
-
DB 스키마 조회:
mcp__claude_ai_Notion__notion-fetch(id=NOTION_DATABASE_ID)- 필드명·타입 매핑 확인. 현재 DB는 title
이름1개뿐. - status/category/tags 필드가 스키마에 없으면 매핑 스킵 (env 빈 값과 동일하게 처리).
- 향후 속성이 추가되면 env 갱신 후 자동 매핑.
- 필드명·타입 매핑 확인. 현재 DB는 title
-
final.md 파싱:
- 첫
#헤더 = 페이지 제목 →이름필드. - 본문 = 나머지 마크다운.
- "SEO 키워드" 섹션 → category 후보 (필드 있으면 매핑).
- "해시태그" 섹션 → tags multi_select 후보 (필드 있을 때만, DB의 기존 옵션만 사용, 새 옵션 만들지 말 것 — [[notion-threads-tags]]).
- 첫
-
사용자에게 발행 미리보기 1줄:
제목: {제목} / DB: 블로그 자동화 (이름 필드) 발행할까요?- 명시적 OK 받기 전 다음 단계 진행 금지.
-
페이지 생성:
mcp__claude_ai_Notion__notion-create-pages( parent={ database_id: NOTION_DATABASE_ID }, properties={ <매핑된 필드> }, content=<final.md 본문> ) -
결과 기록:
workspace/{RUN_ID}/meta.json에 page URL, page ID, published_at 저장.
규칙
- 자동 발행 절대 금지. 한 번의 세션 OK는 한 번의 발행만 허락.
- 태그 multi_select는 DB 기존 옵션만 사용. 새 옵션 자동 생성 시 발행 실패 ([[notion-threads-tags]]).
- Notion 페이지 콘텐츠는 단락 단위로 묶기. 줄마다 따로 블록 만들지 말 것 ([[notion-paragraph-grouping]]).
- JSON escape
\n그대로 보내지 말 것 — 실제 멀티라인 텍스트로 전달 ([[notion-publishing-format]]). - URL은 단락 끝에만, 인라인 삽입 금지 ([[url-placement]]).
- 실패 시 retry 1회. 두 번째 실패는 즉시 stdout에 사유 출력 후 중단.
완료 조건
meta.json에 page_url 존재. 사용자에게 URL 1줄 회신.
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.
- 10d ago Changed · +1 lines 2aa54d0d644d
- 2mo ago First seen · 78 lines · 31 tokens per session scan A d559824e24bf
blog-publisher is an agent published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 922 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
blog-publisher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-publisherunclejobs-ai/blog-posting-auto | Agent | 42 | 6d ago | MIT | A | 31 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |