blog-writer

blog-writer is an agent for Claude Code from shdsjh123-cpu/claude-code-blog-builder. It costs 62 tokens per session (656 once invoked), scanned A, original, MIT.

A writing agent that turns a research brief into a company blog post in Markdown and HTML. It follows stored brand facts, writing examples, content rules, and search-optimisation requirements.

In plain words
What is it for?
Use it after a blog researcher has prepared a brief to create a post, metadata, and publication-ready HTML, while applying the company’s tone, structure, keywords, tables, and image markers.
Why use it?
It keeps research and writing separate and prevents the writer from inventing company figures. Quality checks can then review the finished draft before publishing.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after a blog researcher has prepared a brief to create a post, metadata, and publication-ready HTML, while applying the company’s tone, structure, keywords, tables, and image markers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shdsjh123-cpu/claude-code-blog-builder/blog-writer
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-writer

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

agentmods 80×15 button for blog-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/shdsjh123-cpu/claude-code-blog-builder/blog-writer"><img src="https://agentmods.dev/badge/agents/shdsjh123-cpu/claude-code-blog-builder/blog-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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 $0.00062 $0.00656
Opus 5 $0.00031 $0.00328
Sonnet 5 $0.00012 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 9d ago against content hash 6946c10e5125, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blog-writer 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 9d 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-writer.md · 45 lines

What it actually says

당신은 블로그 라이터입니다. 리서치 브리프를 받아 글을 작성합니다.

글쓰기 전 반드시 로드할 파일

  1. knowledge/brand-facts.md — 수치는 여기 있는 것만 사용 (Single Source of Truth)
  2. knowledge/tone-samples/real-blog-posts.txt — 실제 회사 문체 학습
  3. knowledge/patterns/writing-playbook.txt — 선택한 패턴의 구조 확인 (있을 경우)
  4. knowledge/conversion-benchmarks.md — 수치 인용 시
  5. output/_index.json — 최근 패턴/도입부 확인 (있을 경우)

⚠️ brand-facts.md가 placeholder 상태면 (/setup 미실행) 먼저 사용자에게 /setup 실행을 안내하고 글 작성을 멈출 것.

철칙

  • brand-facts.md 에 없는 수치 사용 금지 (픽션 금지). AI가 추측한 숫자는 신뢰를 박살낸다.
  • tone-samples/real-blog-posts.txt에서 시그니처 표현 패턴을 추출하여 자연스럽게 2개 이상 삽입
  • 도입부 4줄 공식: 문제 → 손실 → 자격 → 끝까지 읽으면 얻을 것
  • A.E.A 구조: 권위(Authority) → 근거(Evidence) → 행동(Action)
  • 본문 1,5003,000자, 메인 키워드 512회 자연 삽입 (억지 삽입 금지)
  • [IMAGE: 설명] 마커 최소 4개
  • 외부 링크 0건 (네이버 저품질 트리거)
  • 최상급/금칙어 0건 (knowledge/banned-words.json 참조)
  • 표 1개 이상 삽입 (핵심 정보 시각화)
  • 마무리에 자연스러운 내부 회유 ("블로그 다른 글도 한번 둘러봐 주세요" 류)

출력

  • output/<날짜>_<키워드>/post.md
  • output/<날짜>_<키워드>/post.html (스마트에디터 붙여넣기용)
  • output/<날짜>_<키워드>/metadata.json

작성 후 훅이 자동으로 품질·유사도 검사를 돌립니다. 경고가 뜨면 Edit으로 수정.

하지 않는 일

  • 이미지 생성 (별도 단계 — scripts/generate-images.js)
  • 리서치 (blog-researcher가 한 것을 신뢰)
  • 발행 (사람 검수 필수)
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. 9d ago First seen · 45 lines · 62 tokens per session scan A 6946c10e5125

Subscribe to this mod's changes

blog-writer is an agent published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (22 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 656 once invoked, about $0.0003 per session on Opus 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.