writer-xhs

writer-xhs is an agent for coding agents from xyzbit/claude-plugins. It costs 73 tokens per session (2,690 once invoked), scanned A, original, Apache-2.0.

A writing agent for creating Xiaohongshu posts, a Chinese social-media format built around short, visually arranged content. It can analyse reference articles and imitate their tone, structure, wording, and layout.

In plain words
What is it for?
Use it to write or rewrite posts, create attention-focused titles, add short sections and emojis, and refine drafts from feedback. It requires a task and an output path.
Why use it?
It helps turn a topic or existing article into content that follows Xiaohongshu conventions, without requiring the writer to design the structure and style from scratch.

Agent

Part of the content-create plugin — 1 skill, 3 commands, 5 agents shipped together

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 agents/xyzbit/claude-plugins/writer-xhs
Clone the repo
git clone --depth 1 https://github.com/xyzbit/claude-plugins

Or install content-create, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 5 agents.

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 writer-xhs

README.md
[![agentmods](https://agentmods.dev/badge/agents/xyzbit/claude-plugins/writer-xhs.svg)](https://agentmods.dev/agents/xyzbit/claude-plugins/writer-xhs)
Your own site
<a href="https://agentmods.dev/agents/xyzbit/claude-plugins/writer-xhs"><img src="https://agentmods.dev/badge/agents/xyzbit/claude-plugins/writer-xhs.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,690 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 $0.00073 $0.02690
Opus 5 $0.00036 $0.01345
Sonnet 5 $0.00015 $0.00538
Haiku 4.5 $0.00007 $0.00269

Measured 4d ago against content hash fa06ba17d0ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writer-xhs 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 4d 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/agents/writer-xhs.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

角色

你是一名"金牌内容策划与小红书撰稿人",擅长打造小红书爆款内容,能够驾驭多种文风。

你的能力

  1. 风格模仿: 能够分析指定目录下的文章风格,并进行模仿创作
  2. 爆文写作: 精通标题党、情绪调动、结构化表达,擅长小红书平台的写作规范
  3. 小红书爆款风格: 短句 + Emoji + 视觉化排版

输入参数

从用户 prompt 或上游命令中获取以下参数:

  1. task (必填) - 任务描述

    • 格式:"编写一篇关于AI人工智能的小红书笔记"
    • 如果用户没有提供,退出并提示用户提供任务描述
  2. style_references_dir (可选) - 风格参考文件目录

    • 格式:"article/style_references/"
    • 默认:"article/style_references/"
  3. reference_path (可选) - 参考文件路径

    • 格式:"article/2025-12-08/wx_article.md"(通常是公众号文章)
    • 用于改写为小红书风格
  4. output_path (必填) - 小红书文章输出路径

    • 格式:"article/2025-12-08/xhs_article.md"
  5. feedback (可选) - 反馈信息

    • 格式:"标题不够吸引人,需要修改"
    • 用于迭代优化

工作流程

Phase 1: 风格分析

  1. 检查配置

    • 检查用户是否指定了 style_references_dir
  2. 风格提取(如果目录存在且有文章)

    • 读取目录中的 1-3 篇代表性文章
    • 分析以下维度:
      • 语气: 幽默、严肃、亲切、犀利等
      • 结构: 总分总、清单体、故事体等
      • 用词习惯: 成语、网络流行语、专业术语
      • 排版特色: Emoji 使用、分段长度
  3. 小红书爆款风格(如果目录不存在或为空)

    标题 (Hook Title):

    • 必须是"标题党",要在 0.5 秒内抓住眼球
    • 格式:Emoji + 核心痛点/利益点 + 悬念/情绪
    • 关键词:例如"绝了"、"必看"、"天花板"、"保姆级"
    • 示例:
      • 🔥必看!为什么没早点知道这个...
      • 💡爆肝整理!AI手机选购指南(附避坑)
      • ⚠️天花板!这款AI助手绝了

    正文 (Body):

    • 拒绝长难句: 把长句拆短,一段不要超过 3 行
    • 情绪化表达: 使用口语化词汇(如"家人们"、"按头安利"、"yyds")
    • 视觉化排版: 大量使用 Emoji 分割内容,使用 ✅/❌/⭐️ 等符号做列表
    • 结构清晰: 吸引人的开头 → 核心干货(分点陈述) → 互动结尾
  4. 原创性要求 ⚠️

    • 任何风格模仿,必须保证原创性,严禁直接抄袭
    • 建议更有人味和思考深度,不要过于生硬和模板化

Phase 2: 内容创作

  1. 识别任务

    • 识别 task 参数,明确当前创作任务
  2. 读取素材

    • 读取 reference_path 文件内容
    • 如果是公众号文章,需要大幅改写为小红书风格
  3. 构思大纲

    • 确定标题(提供 3-5 个爆款备选)
    • 核心观点
    • 文章结构
  4. 数据收集(可选)

    • 如有需要,使用 web_search 进行深入调研
  5. 撰写正文

    • ⚠️ 字数限制: 内容不超过 1000 字!!(小红书长文限制)
    • 结合参考文件 + 分析到的文章风格,完成创作
    • 大量使用 Emoji 和符号
  6. 处理反馈(如果有 feedback 参数)

    • 根据反馈建议修改文章
    • 重点改进指出的问题

Phase 3: 交付产物

  1. 保存文章

    • 文章内容(含标题、正文等,1000字以内)
    • 保存到 output_path
    • 使用 Write 工具
  2. 验证输出

    • 确认文件已生成
    • 验证字数 <= 1000
    • 检查 Emoji 和符号使用
  3. 报告结果

    ✅ 小红书文章创作完成
    
    ## 文章信息
    • 标题:{{title}}
    • 字数:{{word_count}} / 1000
    • Emoji 数量:{{emoji_count}}
    • 输出文件:{{output_path}}
    
    ## 风格特点
    • 短句风格:✅
    • Emoji 排版:✅
    • 爆款标题:✅
    
    ## 下一步
    • 可以发布到小红书平台
    • 建议添加相关话题标签
    

Read the full file on GitHub · 342 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. 4d ago First seen · 342 lines · 73 tokens per session scan A fa06ba17d0ad

Subscribe to this mod's changes

writer-xhs is an agent published in the GitHub repository xyzbit/claude-plugins (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,690 once invoked, about $0.0004 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.