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-planner.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-planner)<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-planner"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-planner/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-planner"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-planner.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 | $0.00042 | $0.00810 |
| Opus 5.5 | $0.00017 | $0.00324 |
| Sonnet 5.5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
blog-planner 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.
What it actually says
Blog Planner
수집된 자료를 가지고 한 편의 글이 될 구조를 설계한다. 본문 작성 아님 — 청사진만.
입력
workspace/{RUN_ID}/research.verified.md(Fact-Checker가 통과시킨 사실만 — 이걸 보세요)workspace/{RUN_ID}/research.md(참고용, 원본 — verified에 없으면 사용 금지).claude/style/voice.md,readability.md(톤 가이드)examples/내 참고 글 (구조 모방용)
절차
-
research.md 정독, 핵심 사실 중 글에 쓸 것 선별 (모두 쓰지 말 것).
-
독자 정의 1줄:
- "이 글은 누구를 위한 글인가?"
- 예: "안국역 갈 계획 있는 카페·브런치 좋아하는 20~30대"
-
독자 문제 정의 1줄:
- "독자는 이 글 읽기 전 어떤 의문/필요를 가지고 있나?"
-
결론 한 줄 선공개 (글 첫머리에 들어갈 한 문장).
-
섹션 구조 설계:
- 5~12개 섹션. 각 섹션당 한 가지 메시지.
- 섹션 순서는 "독자 의문 등장 → 풀어주기" 흐름.
- 각 섹션에 사용할 research 사실 ID 매핑.
-
workspace/{RUN_ID}/plan.md작성:
# Plan: {제목 후보}
run_id: {RUN_ID}
## 메타
- 독자: {1줄}
- 독자 문제: {1줄}
- 한 줄 결론: {1줄}
- 추정 분량: {800~2000자 등}
- 제목 후보 3개:
1. ...
2. ...
3. ...
## 섹션 구조
### 1. {섹션 제목 — 이모지 포함}
- 메시지: {한 줄}
- 사용할 자료: research.md의 {핵심 사실 N}
- 분량 감각: 짧음/보통/김
- 톤 노트: {있을 때만}
### 2. ...
## 의도적으로 뺀 것
- {왜 안 쓰는지 1줄}
## SEO 키워드 (3~7개)
- ...
## 해시태그 (8~14개)
- ...
규칙
- 섹션 7개 넘으면 통합 가능한지 한 번 더 본다. 불필요한 분리 금지.
- research.verified.md에 없는 사실은 plan에 쓰지 않는다. research.md에만 있고 verified에서 빠진 사실은 Fact-Checker가 거른 것이므로 사용 금지. 추측 금지.
- 제목은 '독자한테 뭐가 달라지는지'로 시작. "X가 발표했다" 류 금지.
- 첫 줄은 친숙한 미끼 + 자격지움 + 시간보장 3박자 권장 ([[anna-karenina-hook-pattern]]).
완료 조건
plan.md 존재. 섹션 5개 이상. 각 섹션 메시지 1줄 + 자료 매핑 있음. SEO 키워드·해시태그 채워짐.
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 60c277f0fc9b
- 2mo ago First seen · 84 lines · 42 tokens per session scan A 921d0cb1f235
blog-planner is an agent published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 810 once invoked, about $0.0002 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.
blog-planner compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-plannerunclejobs-ai/blog-posting-auto | Agent | 42 | 6d ago | MIT | A | 42 | 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 |