agentmods.dev

claude-code-blog-builder: Instructions file for Claude Code

CLAUDE.md

claude-code-blog-builder CLAUDE.md is an instructions file for Claude Code from shdsjh123-cpu/claude-code-blog-builder. It costs 2,907 tokens per session, scanned A, original, MIT.

A project instruction file for a tool that creates blog posts from keywords, including research, drafts, images, quality checks, and publishing assistance. It also documents setup commands and the project's folders.

In plain words
What is it for?
Use it when developing or running this blog automation project, especially for setup, tone configuration, domain configuration, and creating new blog posts.
Why use it?
It gives the coding agent the project-specific rules and workflow needed to operate the blog builder correctly.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is shdsjh123-cpu/claude-code-blog-builder's own configuration. It tells Claude Code how to work on claude-code-blog-builder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-blog-builder configures β†’

not rated 21repo 5mo ago A scan 2,907 tokens original MIT
View source β†— shdsjh123-cpu/claude-code-blog-builder
Reuse

Borrowing it

Nothing to install: this file belongs to shdsjh123-cpu/claude-code-blog-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shdsjh123-cpu/claude-code-blog-builder/main/CLAUDE.md
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 claude-code-blog-builder CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shdsjh123-cpu/claude-code-blog-builder/claude-md.svg)](https://agentmods.dev/instructions/shdsjh123-cpu/claude-code-blog-builder/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shdsjh123-cpu/claude-code-blog-builder/claude-md"><img src="https://agentmods.dev/badge/instructions/shdsjh123-cpu/claude-code-blog-builder/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,907 This file is loaded in full into every session.
When invoked 2,907 The same file β€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file β€” 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 $0.02907 $0.02907
Opus 5 $0.01453 $0.01453
Sonnet 5 $0.00581 $0.00581
Haiku 4.5 $0.00291 $0.00291

Measured 8d ago against content hash ab8a9be4ad89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-code-blog-builder CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” measured 8d 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.md Β· 284 lines

How it starts

The opening of the file, as written. The whole thing β€” 284 lines β€” stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Blog Builder

이 ν”„λ‘œμ νŠΈλŠ” Claude Codeμ—μ„œ 직접 μ‹€ν–‰ν•˜λŠ” λΈ”λ‘œκ·Έ μ½˜ν…μΈ  μžλ™ν™” λ„κ΅¬μž…λ‹ˆλ‹€. μ‚¬μš©μžκ°€ "이 ν‚€μ›Œλ“œλ‘œ λΈ”λ‘œκ·Έ κΈ€ λ§Œλ“€μ–΄μ€˜"라고 μš”μ²­ν•˜λ©΄ ν‚€μ›Œλ“œ λ¦¬μ„œμΉ˜ β†’ μ΄ˆμ•ˆ 생성 β†’ 이미지 생성 β†’ ν’ˆμ§ˆ 검증 β†’ λ°œν–‰ μ–΄μ‹œμŠ€ν„΄νŠΈκΉŒμ§€ μˆ˜ν–‰ν•©λ‹ˆλ‹€.

⚠️ 이 μ‹œμŠ€ν…œμ€ 1개 λΈ”λ‘œκ·Έλ₯Ό 직접 μš΄μ˜ν•˜λŠ” κ²½μš°μ— μ΅œμ ν™”λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€. λ©€ν‹° μΉ΄ν…Œκ³ λ¦¬ 운영, μ €ν’ˆμ§ˆ 볡ꡬ, λ°œν–‰ μŠ€μΌ€μ€„λ§, μ™Έμ£ΌνŒ€ μ›Œν¬ν”Œλ‘œμš° 등은 μƒμœ„ μ†”λ£¨μ…˜μ΄ ν•„μš”ν•©λ‹ˆλ‹€.

πŸš€ 처음 μ‚¬μš©ν•œλ‹€λ©΄ β€” /setup λΆ€ν„°

이 λ ˆν¬λŠ” λˆ„κ΅¬λ‚˜ 자기 νšŒμ‚¬μ— 맞게 μ‚¬μš©ν•  수 μžˆλ„λ‘ ν…œν”Œλ¦Ών™”λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€. 처음 clone λ°›μ•˜λ‹€λ©΄ κ°€μž₯ λ¨Όμ € λ‹€μŒ λͺ…령을 μ‹€ν–‰ν•˜μ„Έμš”:

/setup

5λΆ„ 인터뷰λ₯Ό 톡해 knowledge/brand-facts.mdκ°€ μžλ™μœΌλ‘œ μ±„μ›Œμ§€λ©°, 이후 /blog-new "ν‚€μ›Œλ“œ" ν•œ μ€„λ‘œ κΈ€ ν•œ 편이 λ‚˜μ˜΅λ‹ˆλ‹€.

Phase 1 (5λΆ„, ν•„μˆ˜) β†’ /setup Phase 2 (10λΆ„, ꢌμž₯) β†’ /setup-tone (μ—¬λŸ¬λΆ„ νšŒμ‚¬ λΈ”λ‘œκ·Έ URLμ—μ„œ 톀 μžλ™ ν•™μŠ΅) Phase 3 (15λΆ„, 선택) β†’ /setup-domain (μΉ΄ν…Œκ³ λ¦¬λ³„ ν‚€μ›Œλ“œ 뱅크 + 산업별 κΈˆμΉ™μ–΄)

ν”„λ‘œμ νŠΈ ꡬ쑰

claude-code-blog-builder/
β”œβ”€β”€ CLAUDE.md              # 이 파일 (Claude Code μ§€μ‹œμ„œ)
β”œβ”€β”€ README.md
β”œβ”€β”€ INSTALL.md             # 30초 μ„€μΉ˜ κ°€μ΄λ“œ
β”œβ”€β”€ package.json           # μ™ΈλΆ€ μ˜μ‘΄μ„± 0
β”‚
β”œβ”€β”€ knowledge/             # ⭐ Single Source of Truth
β”‚   β”œβ”€β”€ README.md
β”‚   β”œβ”€β”€ brand-facts.template.md          # 곡개 ν…œν”Œλ¦Ώ
β”‚   β”œβ”€β”€ brand-facts.md                   # /setup이 생성 (gitignored)
β”‚   β”œβ”€β”€ conversion-benchmarks.template.md
β”‚   β”œβ”€β”€ conversion-benchmarks.md
β”‚   β”œβ”€β”€ banned-words.template.json
β”‚   β”œβ”€β”€ banned-words.json
β”‚   β”œβ”€β”€ tone-samples/                    # /setup-tone이 채움
β”‚   └── patterns/
β”‚
β”œβ”€β”€ scripts/
β”‚   β”œβ”€β”€ research.js              # 넀이버 API ν‚€μ›Œλ“œ λ¦¬μ„œμΉ˜
β”‚   β”œβ”€β”€ generate-images.js       # Nano Banana Pro 이미지 생성
β”‚   β”œβ”€β”€ quality-check.js         # 7ν•­λͺ© κ²°μ •λ‘  채점
β”‚   β”œβ”€β”€ duplicate-check.js       # 6-gram Jaccard μœ μ‚¬λ„
β”‚   β”œβ”€β”€ hook-post-write.js       # PostToolUse ν›… λΌμš°ν„°
β”‚   β”œβ”€β”€ preview.js               # λ°œν–‰ μ–΄μ‹œμŠ€ν„΄νŠΈ (HTML)
β”‚   β”œβ”€β”€ setup-tone-fetch.js      # λΈ”λ‘œκ·Έ URL λ³Έλ¬Έ μˆ˜μ§‘
β”‚   └── sanitize-check.sh        # push μ „ 게이트
β”‚
β”œβ”€β”€ templates/
β”‚   β”œβ”€β”€ thumbnail.html
β”‚   β”œβ”€β”€ infographic.html
β”‚   └── quote-card.html
β”‚
β”œβ”€β”€ .claude/
β”‚   β”œβ”€β”€ settings.json            # PostToolUse ν›… 등둝
β”‚   β”œβ”€β”€ commands/
β”‚   β”‚   β”œβ”€β”€ setup.md             # /setup
β”‚   β”‚   β”œβ”€β”€ setup-tone.md
β”‚   β”‚   β”œβ”€β”€ setup-domain.md
β”‚   β”‚   β”œβ”€β”€ blog-new.md          # /blog-new
β”‚   β”‚   β”œβ”€β”€ blog-research.md
β”‚   β”‚   β”œβ”€β”€ blog-quality.md
β”‚   β”‚   β”œβ”€β”€ blog-publish-ready.md
β”‚   β”‚   └── blog-preview.md
β”‚   └── agents/
β”‚       β”œβ”€β”€ setup-interviewer.md
β”‚       β”œβ”€β”€ blog-researcher.md
β”‚       β”œβ”€β”€ blog-writer.md
β”‚       β”œβ”€β”€ blog-quality-reviewer.md
β”‚       └── medical-law-checker.md
β”‚
β”œβ”€β”€ keyword-bank/                # μΉ΄ν…Œκ³ λ¦¬λ³„ μ‹œλ“œ ν‚€μ›Œλ“œ
β”‚   β”œβ”€β”€ README.md
β”‚   β”œβ”€β”€ detail-page.yml          # μ˜ˆμ‹œ
β”‚   β”œβ”€β”€ hospital-marketing.yml   # μ˜ˆμ‹œ
β”‚   β”œβ”€β”€ beauty-brand.yml         # μ˜ˆμ‹œ
β”‚   └── ai-marketing.yml         # μ˜ˆμ‹œ
β”‚
β”œβ”€β”€ output/                      # μƒμ„±λœ κ²°κ³Όλ¬Ό (gitignored)
β”‚   └── .gitkeep
β”‚
└── docs/
    β”œβ”€β”€ how-it-works.md
    β”œβ”€β”€ setup-guide.md
    └── troubleshooting.md

Read the full file on GitHub Β· 284 lines

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. 8d ago First seen Β· 284 lines Β· 2,907 tokens per session scan A ab8a9be4ad89

Subscribe to this mod's changes

claude-code-blog-builder CLAUDE.md is an instructions file published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (21 stars, last pushed 5mo ago), licensed MIT. It adds 2,907 tokens to every session, about $0.0145 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.

Marketing and SEOWriting and docs
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js Β· 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex Β· 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode Β· 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode Β· 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain Β· 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart β€” add a new integration in 5 steps, integration architecture and integrationmanifest β€” file tracking.

github/spec-kit Β· 7,104 tokens