Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shdsjh123-cpu/claude-code-blog-buildernpx agentmods add commands/shdsjh123-cpu/claude-code-blog-builder/blog-newWrote 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/commands/shdsjh123-cpu/claude-code-blog-builder/blog-new)<a href="https://agentmods.dev/commands/shdsjh123-cpu/claude-code-blog-builder/blog-new"><img src="https://agentmods.dev/badge/commands/shdsjh123-cpu/claude-code-blog-builder/blog-new/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/commands/shdsjh123-cpu/claude-code-blog-builder/blog-new"><img src="https://agentmods.dev/badge/commands/shdsjh123-cpu/claude-code-blog-builder/blog-new.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 | $0.00030 | $0.00839 |
| Opus 5 | $0.00015 | $0.00419 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
blog-new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
사용자가 "$ARGUMENTS" 키워드로 블로그 글을 만들어달라고 요청했습니다.
⚠️ 사전 체크:
knowledge/brand-facts.md가 placeholder 상태([PLACEHOLDER]로 시작)면 먼저 사용자에게/setup실행을 안내하고 중단하세요. /setup 없이 글을 쓰면 회사 정보가 빠진 일반 글이 나옵니다.
CLAUDE.md의 실행 파이프라인에 따라 아래 순서를 반드시 전부 수행하세요:
0. 사전 로드 (생략 금지)
다음 파일을 먼저 Read로 읽습니다:
knowledge/brand-facts.md— 회사 수치·인증·자사 제품 정보 (Single Source of Truth)knowledge/tone-samples/real-blog-posts.txt— 실제 회사 블로그 문체 (있을 경우)knowledge/patterns/writing-playbook.txt— 글쓰기 패턴 가이드 (있을 경우)knowledge/banned-words.json— 금칙어 (도메인 단어 포함)output/_index.json— 최근 사용한 패턴/도입부 확인 (있을 경우 — 의도적으로 다른 조합 선택)
1. 키워드 리서치 (STEP 1)
set -a && . ./.env && set +a && node scripts/research.js --keyword "$ARGUMENTS" --output "output/$(date +%Y-%m-%d)_$(echo $ARGUMENTS | tr -d ' ')"
API 인증 실패 시 웹 검색 기반으로 대체 리서치.
2. 콘텐츠 생성 (STEP 2)
blog-writer서브에이전트에 위임 또는 직접 작성- 12패턴 중 가장 적합한 것 1~2개 선택 (최근 글과 다른 것)
- A.E.A 구조 + 도입부 4줄 공식 + 문체 변주 규칙 준수
post.md와post.html작성output/<폴더>/에 저장 → 훅이 자동으로 품질검사·유사도검사 실행
3. 이미지 생성 (STEP 3)
set -a && . ./.env && set +a && node scripts/generate-images.js \
--title "..." --keyword "$ARGUMENTS" \
--points "..." --quote "..." --steps "..." \
--output "output/<폴더>/images"
브랜드명/컬러팔레트는 환경변수로 주입됨 (/setup-domain에서 설정).
4. 품질 검증 (STEP 4)
훅이 자동 실행하지만, 경고가 나오면 본문을 수정하고 재검사.
의료/뷰티 키워드인 경우 medical-law-checker 서브에이전트도 호출.
5. 최종 패키지 (STEP 5)
metadata.json(패턴 번호·톤 변주·품질 리포트)guide.md(편집 가이드 · 사실 확인 체크리스트 · 이미지 삽입 위치)output/_index.json에 새 글 항목 추가 +recent_rotation갱신
완료 후 사용자에게 보고할 것
- 제목 / 글자수 / 패턴 / 톤 변주 조합
- 품질검사 결과, 유사도 검사 결과
- 이미지 4장 생성 여부
- 발행 전 사람이 확인해야 할 항목 (수치·레퍼런스)
- 다음 단계:
/blog-preview <폴더>로 발행 어시스턴트 실행
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 First seen · 58 lines · 30 tokens per session scan A 5fc063f1273d
blog-new is a command published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (22 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 839 once invoked, about $0.0002 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.