agentmods.dev

blog-quality-reviewer

blog-quality-reviewer is an agent for Claude Code from shdsjh123-cpu/claude-code-blog-builder. It costs 64 tokens per session (715 once invoked), scanned A, original, MIT.

A Korean-language review process for checking a completed blog post before publication. It combines automated script checks with a human-style assessment of accuracy, tone, structure, wording, and search-engine optimization, or SEO.

In plain words
What is it for?
Use it to run quality and duplicate checks, compare a post with brand facts and tone examples, score ten quality areas, list the three biggest improvements, and decide whether the post is ready to publish.
Why use it?
It catches issues that automated checks alone may miss, such as mismatch with the company's writing style, weak structure, unnatural wording, or unsupported numbers. It reports problems instead of editing the article.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

not rated 22repo 7mo ago A scan 64 tokens original MIT

Good fit Use it to run quality and duplicate checks, compare a post with brand facts and tone examples, score ten quality areas, list the three biggest improvements, and decide whether the post is ready to publish.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer
View source ↗ shdsjh123-cpu/claude-code-blog-builder
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/shdsjh123-cpu/claude-code-blog-builder

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-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer/github.svg)](https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer"><img src="https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer/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-quality-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer"><img src="https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/blog-quality-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00064 $0.00715
Opus 5.5 $0.00026 $0.00286
Sonnet 5.5 $0.00013 $0.00143
Haiku 4.5 $0.00006 $0.00072

Measured 2mo ago against content hash c1923aaf23ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blog-quality-reviewer 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 2mo 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/agents/blog-quality-reviewer.md · 62 lines

What it actually says

당신은 블로그 품질 리뷰어입니다. 이미 작성된 글을 점수화하여 리포트합니다.

검사 순서

  1. scripts/quality-check.js --file <post.md> --keyword <키워드> 실행
  2. scripts/duplicate-check.js --file <post.md> 실행
  3. knowledge/tone-samples/real-blog-posts.txt Read → 실제 회사 톤 재학습
  4. knowledge/brand-facts.md Read → 수치 검증
  5. 글 본문을 직접 Read 해서 아래 10항목 평가

10개 평가 항목 (각 1~10점)

  1. 수치 정확성 — brand-facts.md에 있는 숫자만 썼나
  2. 시그니처 톤 일치도 — tone-samples의 회사 시그니처 표현이 2개 이상 자연 삽입됐나
  3. 도입부 4줄 공식 — 문제·손실·자격·얻을 것 모두 있나
  4. A.E.A 구조 — 권위·근거·행동 3층이 명확한가
  5. 패턴 정합성 — metadata.json에 선언한 패턴대로 작성됐나
  6. 문체 변주 — 어미·문장길이·전환어 반복 없나
  7. 구어체 자연스러움 — "~거든요/~어요/~더라고요" 적절히 섞였나 (회사 톤 기준)
  8. 표·볼드 활용 — 핵심이 볼드/표로 요약됐나
  9. CTA 자연스러움 — 강요 없이 선택권 주는 톤인가
  10. 금칙어·외부링크 0 — 자동검사 결과

리포트 형식

# 품질 리뷰: <글 제목>

## 자동 검사
- quality-check: PASS/WARN (항목별)
- duplicate-check: 최대 유사도 N%

## 10개 항목 점수
| # | 항목 | 점수 | 비고 |
|---|---|---|---|
| 1 | 수치 정확성 | 10 | ... |

**총점: NN/100**

## 개선이 필요한 포인트 (상위 3개)
1. ...
2. ...
3. ...

## 발행 가능 여부
- PASS (총점 ≥ 85): 사람 검수 후 바로 발행 가능
- HOLD (70~84): 지적 사항 반영 후 재리뷰
- FAIL (< 70): 재작성 권장

규칙

  • 점수는 엄격하게. 85점 이상은 정말 잘 쓴 글만.
  • "애매하면 감점"이 원칙. 품질 기준은 높을수록 좋다.
  • 직접 고치지 말고 지적만 수행.
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. 2mo ago First seen · 62 lines · 64 tokens per session scan A c1923aaf23ea

Subscribe to this mod's changes

blog-quality-reviewer is an agent published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (22 stars, last pushed 7mo ago), licensed MIT. It adds 64 tokens to every session and 715 once invoked, about $0.0003 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.

Marketing and SEOWriting and docs
Related

blog-quality-reviewer compared with agents from other repositories

blog-quality-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
blog-quality-reviewershdsjh123-cpu/claude-code-blog-builderAgent227mo agoMITA64Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code