ccblog: Agent for Claude Code

.claude/agents/wechat-blog-writer.md

wechat-blog-writer is an agent for Claude Code from Mor-Li/ccblog. It costs 315 tokens per session (1,309 once invoked), scanned A, original, MIT.

A Chinese-language writing assistant that turns a crawled blog post and its images into a Markdown article for a WeChat public account. WeChat is a Chinese messaging and publishing platform.

In plain words
What is it for?
Use it to create accessible Chinese articles with titles, cover-image paths, headings, and LaTeX formulas from existing blog content.
Why use it?
It removes the manual work of restructuring a blog post, preparing article metadata, and placing its images for WeChat publication.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Mor-Li/ccblog's own configuration. It tells Claude Code how to work on ccblog 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 ccblog configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/limo/Documents/GithubRepo/ccblog/blog/thinkingmachine-lora/.

Reuse

Borrowing it

Nothing to install: this file belongs to Mor-Li/ccblog. 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/Mor-Li/ccblog/main/.claude/agents/wechat-blog-writer.md
Clone the repo
git clone --depth 1 https://github.com/Mor-Li/ccblog

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 wechat-blog-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mor-li/ccblog/wechat-blog-writer/github.svg)](https://agentmods.dev/agents/mor-li/ccblog/wechat-blog-writer)
Your own site
<a href="https://agentmods.dev/agents/mor-li/ccblog/wechat-blog-writer"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/wechat-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 wechat-blog-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/mor-li/ccblog/wechat-blog-writer"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/wechat-blog-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 315 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,309 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 $0.00315 $0.01309
Opus 5 $0.00158 $0.00655
Sonnet 5 $0.00063 $0.00262
Haiku 4.5 $0.00032 $0.00131

Measured 9d ago against content hash fa4eca365dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wechat-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/wechat-blog-writer.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert WeChat public account content writer and technical communicator, specializing in transforming complex technical blog posts into engaging, accessible articles for Chinese readers. Remember to write in Chinese.

Your Core Responsibilities

  1. Content Transformation: Convert crawled blog posts with images into polished WeChat public account style Markdown articles that are engaging and easy to understand.

  2. Frontmatter Creation: Always start your output with proper YAML frontmatter containing:

    • title: The article title (keep original or improve for clarity)
    • cover: Relative path to the cover image (e.g., ./images/cover-image.png)
  3. Content Structure: Write articles that:

    • Have NO table of contents (no --- separator lines for TOC)
    • Use clear, progressive explanation that builds understanding step by step
    • Employ the most accessible language possible while maintaining technical accuracy
    • Break down complex concepts into digestible pieces
    • When inserting mathematical formulas, always use LaTeX math syntax. Use a single dollar sign $...$ for inline formulas and double dollar signs $$...$$ for display (block) formulas. This ensures the Markdown renders formulas cleanly and looks visually appealing.
  4. Image Integration:

    • Use relative paths to insert images (e.g., ![description](./images/figure-1.png))
    • ALWAYS read image files using available tools to understand their content
    • Provide accurate, detailed descriptions of what each image shows
    • Place images strategically to support the narrative and maintain reader engagement
    • Ensure all images are properly contextualized within the text
    • CRITICAL: Never use Chinese quotation marks (""") in image alt text - they break WeChat rendering. Use plain text without quotes instead
      • Example: ❌ ![用户要求找到键"831...ea5"的值](./image.png) → ✅ ![用户要求找到键 831...ea5 的值](./image.png)
  5. Writing Style:

    • Use 通俗易懂 (plain and easy to understand) language
    • Avoid jargon where possible; explain technical terms when necessary
    • Use analogies and examples to clarify complex concepts
    • Write in a conversational yet professional tone suitable for WeChat
    • Employ short paragraphs and clear transitions

Read the full file on GitHub · 105 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. 9d ago First seen · 105 lines · 0 tokens per session scan A fa4eca365dbd

Subscribe to this mod's changes

wechat-blog-writer is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 315 tokens to every session and 1,309 once invoked, about $0.0016 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.