content:write

A content-creation command that collects information, writes and reviews an article, and publishes it to selected platforms.

In plain words
What is it for?
It creates a dated workspace, reads content settings, accepts a topic and platform choices, and can publish to WeChat, Xiaohongshu, or Feishu with an optional review step.
Why use it?
It brings several content tasks into one workflow instead of requiring separate commands for research, drafting, review, and publishing.

Command

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.

agentmods
npx agentmods add commands/xyzbit/claude-plugins/write
Clone the repo
git clone --depth 1 https://github.com/xyzbit/claude-plugins
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.02680
Opus 5 $0.00013 $0.01340
Sonnet 5 $0.00005 $0.00536
Haiku 4.5 $0.00003 $0.00268

Measured 2d ago against content hash 6c1810bb0f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content:write 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 2d 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.

content-create/commands/write.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Creation Workflow Command

你现在需要执行完整的内容创作工作流,从热点收集到多平台发布。

输入参数

从用户输入中解析以下参数:

必填参数:

  • topic: 创作主题或关键词(用户输入的主要文本)

可选参数(格式:key:value):

  • platforms: 发布平台,可选值 wx(公众号)、xhs(小红书)、feishu(飞书),多个用逗号分隔,默认:wx,xhs
  • skip-review: 跳过评审环节,可选值 true/false,默认:false
  • workspace: 自定义工作空间路径,默认:article/{YYYY-MM-DD-HH-MM}

示例输入:

/content-create:write "AI手机热点分析"
/content-create:write "DeepSeek V3评测" platforms:wx
/content-create:write "AI编程工具" platforms:wx,xhs skip-review:true

执行步骤

Step 0: 初始化

  1. 解析参数

    • 提取 topic 和可选参数
    • 验证参数有效性
  2. 读取配置

    • 读取 .claude/content-create.local.md 配置文件, 获取后续步骤需要用到的变量
    • 如果配置文件不存在,提示用户创建:
      配置文件不存在,请先创建配置文件:
      mkdir -p .claude
      cp ~/.claude/plugins/content-create/templates/content-create.local.md .claude/
      
    • 解析 YAML frontmatter,获取:
      • rss_sources: RSS 源列表
      • time_range: 时间范围
      • paths: 路径配置
      • platforms: 平台配置
  3. 验证配置 检查配置完整性:

    • 如果开启了公众号,则需要配置微信公众号的 app_id 和 app_secret
    • 如果开启了小红书,则需要配置小红书的 app_id 和 app_secret
    • 如果开启了飞书,则需要配置飞书的 app_id 和 app_secret,chat_id 检测到配置不完整,提示用户:"配置不完整,请先配置配置文件"
  4. 生成工作空间

    • 获取当前时间,格式:YYYY-MM-DD-HH-MM
    • 创建工作空间目录:{workspace_root}/{YYYY-MM-DD-HH-MM}/
    • 示例:article/2025-12-08-16-30/
  5. 变量替换

    • 将配置中的 {work-space} 替换为实际工作空间路径
    • 生成文件路径:
      • hot_topic_data_path: {workspace}/hot_topic_data.md
      • wx_article_path: {workspace}/wx_article.md
      • xhs_article_path: {workspace}/xhs_article.md
      • review_report_path: {workspace}/review_report.md

Step 1: 数据收集

调用 collector agent,传递以下参数:

请收集关于"{{topic}}"的热点信息。

参数:
- rss_sources: {{rss_sources}}
- hot_topic_data_path: {{hot_topic_data_path}}
- time_range: {{time_range}}

请生成热点数据文件,包含:
1. 核心热点事件(一句话概括)
2. 关键信息点(5-10条)
3. 舆论风向(正向/负向/争议)
4. 参考素材链接

检查输出

  • 确认 hot_topic_data.md 文件已生成
  • 验证内容是否充实(至少500字)
  • 如果失败,报告错误并终止

Step 2: 公众号文章撰写

如果 {{platforms.wx.enabled}} 为 false,则跳过此步骤,进入 Step 3

调用 writer-wx agent,传递以下参数:

Read the full file on GitHub · 331 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. 2d ago First seen · 331 lines · 26 tokens per session scan A 6c1810bb0f87

Subscribe to this mod's changes

content:write is a command published in the GitHub repository xyzbit/claude-plugins (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 2,680 once invoked, about $0.0001 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.