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.
npx agentmods add skills/luongnv89/claude-howto/blog-draftnpx skills add luongnv89/claude-howto --skill blog-draftgit clone --depth 1 https://github.com/luongnv89/claude-howtoWhat 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 | $0.00047 | $0.02162 |
| Opus 5 | $0.00023 | $0.01081 |
| Sonnet 5 | $0.00009 | $0.00432 |
| Haiku 4.5 | $0.00005 | $0.00216 |
Grade A, and why
blog-draft 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- blog-draft — 91% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding. User should provide:
- Idea/Topic: The main concept or theme for the blog post
- Resources: URLs, files, or references to research (optional but recommended)
- Target audience: Who the blog post is for (optional)
- Tone/Style: Formal, casual, technical, etc. (optional)
IMPORTANT: If the user is requesting updates to an existing blog post, skip steps 0-8 and start directly at Step 9. Read the existing draft file(s) first, then proceed with the iteration process.
Execution Flow
Follow these steps sequentially. Do not skip steps or proceed without user approval where indicated.
Step 0: Create Project Folder
-
Generate a folder name using format:
YYYY-MM-DD-short-topic-name- Use today's date
- Create a short, URL-friendly slug from the topic (lowercase, hyphens, max 5 words)
-
Create the folder structure:
blog-posts/ └── YYYY-MM-DD-short-topic-name/ └── resources/ -
Confirm folder creation with user before proceeding.
Step 1: Research & Resource Collection
-
Create
resources/subfolder in the blog post directory -
For each provided resource:
- URLs: Fetch and save key information to
resources/as markdown files - Files: Read and summarize in
resources/ - Topics: Use web search to gather up-to-date information
- URLs: Fetch and save key information to
-
For each resource, create a summary file in
resources/:resources/source-1-[short-name].mdresources/source-2-[short-name].md- etc.
-
Each summary should include:
# Source: [Title/URL] ## Key Points - Point 1 - Point 2 ## Relevant Quotes/Data - Quote or statistic 1 - Quote or statistic 2 ## How This Relates to Topic Brief explanation of relevance -
Present research summary to user.
Step 2: Brainstorm & Clarify
- Based on the idea and researched resources, present:
- Main themes identified from research
- Potential angles for the blog post
- Key points that should be covered
- Gaps in information that need clarification
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 283 lines · 47 tokens per session scan A 9b2b759fc2cb
blog-draft is a skill published in the GitHub repository luongnv89/claude-howto (41,271 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 2,162 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 skills, from other repositories
docs-page
三栏文档页: 侧导航 + 正文 + 右 TOC.
dg-piagent
Use when working with pi-agent / @earendil-works/pi-coding-agent SDK — 创建 agent、自定义工具、 编写扩展、修改系统提示词、管理会话、配置模型、处理认证、加载 skills/prompts/context files、 实现完全控制模式、或任何需要调用 pi-agent SDK API 的任务时使用。 也用于企业内网接口接入评估：用户给出企业/内网 LLM 接口文档或地址，问「能不能接」「怎么配」时， 按接口核对清单给出接入建议 + models.json 配置初稿。…
agentic-system-reviewer
Use when reviewing agent PRDs, implementation plans, unfinished ideas, or agent code against the Production-grade agentic systems course, especially when scope, archetype, chapter relevance, or course-aligned design quality is uncertain.
how-to-tutorial-writer
Write how-to guides and tutorials that naturally integrate affiliate product recommendations. Triggers on: "write a how-to guide", "tutorial for [task]", "step by step guide to [goal]", "how to [verb] with [product]", "write a tutorial blog post", "guide on how to [task]", "beginner guide to [topic]", "walkthrough for…
review
Skill "review" from vitoworleone/claude-code-handbook, covering 任务, 步骤, 输出格式, 审查报告 and critical.
create-agent-dotnet
This skill creates a durable AI agent application in .NET using Microsoft Agent Framework on Dapr Workflow. Use this skill when the user asks to "create an agent in .NET", "build an agent app in C#", or "scaffold a .NET agent with Microsoft Agent Framework".