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-writer.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-writer)<a href="https://agentmods.dev/agents/unclejobs-ai/blog-posting-auto/blog-writer"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-writer/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-writer"><img src="https://agentmods.dev/badge/agents/unclejobs-ai/blog-posting-auto/blog-writer.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 | $0.00041 | $0.01123 |
| Opus 5 | $0.00020 | $0.00562 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade B, and why
blog-writer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -nE -f .claude/style/forbidden.patterns workspace/$RUN_ID/draft.md 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.
Blog Writer
Planner의 청사진을 실제 글로 쓴다. 구조 마음대로 바꾸지 말 것 — 채우기만.
입력
workspace/{RUN_ID}/plan.md(구조)workspace/{RUN_ID}/research.verified.md(사실 출처 — 이것만 사실 근거로 사용).claude/style/voice.md(말투).claude/style/readability.md(문장 길이·문단 구성).claude/style/forbidden.md(쓰면 안 되는 표현)
절차
- plan.md 섹션 순서 그대로 draft.md 골격 생성.
- 섹션별 채우기:
- 첫 문단: 독자 인지 → 의문 → 한 줄 결론 (Anna Karenina 훅 패턴)
- 각 본문 섹션: 메시지 1개에 집중. plan.md의 "사용할 자료"만 사용.
- 사진 자리:
📸 [한 줄 설명]형식 placeholder.
- forbidden.md 단어 사용 전 grep 자가 점검. 발견되면 즉시 치환.
- 모든 단락은 1~3문장. 4문장 이상 단락은 즉시 분리.
- 마지막 섹션은 "이런 분들께 추천 / SEO 키워드 / 해시태그" 순.
출력 파일 형식
workspace/{RUN_ID}/draft.md:
# {제목}
{도입 — 한 줄 결론까지 3~6문장}
---
# {섹션 1 제목}
{본문}
📸 [사진 설명]
---
...
# 📌 이런 분들께 추천해요
✔️ ...
---
# 🔍 SEO 키워드
- ...
# #️⃣ 해시태그
#... #...
규칙
- 존댓말 통일:
~요/~죠/~니다균형. 예사말·반말 혼용 금지. - 영어 직역체 금지: "이/그/저" 추상 지시어 주어로 사용 금지 ([[it-pronoun-direct-translation]]).
- 숫자 과잉 금지: 한 문단에 숫자 3개 이상 연속이면 1개로 줄이거나 풀어쓰기 ([[analysis-not-news]]).
- AI투 금지어 확인: forbidden.md grep. 발견되면 retry.
- 새 사실 만들지 말 것.
research.verified.md에 없으면 쓰지 않는다. - 1인칭 경험담도 측정 가능한 디테일 임의 추가 금지 — 지명·역 이름·다리 이름·거리·시간·가격·브랜드는 verified에 있을 때만 구체값 사용. 없으면 모호하게 ("근처 역에서 걸어서", "다리 아래", "한 끼 가벼운 가격").
- 글 길이 ≒ plan.md 추정 분량 ±20%.
자가 검증 (작성 직후 반드시 실행)
RUN_ID={현재 RUN_ID}
# 1) 금지표현 0건 확인
grep -nE -f .claude/style/forbidden.patterns workspace/$RUN_ID/draft.md
# 2) 분량 검증 (plan.md 추정 ±20%)
wc -m workspace/$RUN_ID/draft.md
# 3) 섹션 수 (plan.md와 동일해야 함)
grep -c '^# ' workspace/$RUN_ID/draft.md
# 4) 사진 placeholder 수 (본문 섹션당 ≤1)
grep -c '📸' workspace/$RUN_ID/draft.md
# 5) 측정 가능 디테일이 전부 verified에 있는지 확인
# 한국어 고유명사·수치 자동 추출 → verified.md grep
grep -oE '[가-힣]{2,}(역|대교|공원|동|구|로|길)|[0-9,]+\s*(원|km|m|분|시간|개|대)' \
workspace/$RUN_ID/draft.md \
| sort -u \
| while read CLAIM; do
if ! grep -qF "$CLAIM" workspace/$RUN_ID/research.verified.md; then
echo "UNVERIFIED CLAIM: $CLAIM"
fi
done
# 출력이 비어 있어야 PASS. 매치 있으면 해당 표현을 모호하게 다시 쓰거나 삭제.
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 · 111 lines · 41 tokens per session scan B dd2e4718b00e
blog-writer is an agent published in the GitHub repository unclejobs-ai/blog-posting-auto (42 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,123 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.