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 | $0.00917 |
| Opus 5 | $0.00015 | $0.00458 |
| Sonnet 5 | $0.00006 | $0.00183 |
| 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 12d 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.
- 12d 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 3mo ago), licensed MIT. It adds 31 tokens to every session and 917 once invoked, about $0.0002 per session on Opus 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.