auto-replier

auto-replier is an agent for Claude Code from BiboyQG/WeChat-MCP. It costs 39 tokens per session (1,308 once invoked), scanned A, original, MIT.

An assistant that reads the latest messages in a chosen WeChat conversation and drafts and sends a reply based on the context.

In plain words
What is it for?
Use it for brief replies to questions, shared information, invitations, casual messages, work topics, or group chats.
Why use it?
It helps when a message needs a quick response but you do not have time to review the conversation and write one yourself.

Agent for Claude Code

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/biboyqg/wechat-mcp/auto-replier
Clone the repo
git clone --depth 1 https://github.com/BiboyQG/WeChat-MCP

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 auto-replier

README.md
[![agentmods](https://agentmods.dev/badge/agents/biboyqg/wechat-mcp/auto-replier.svg)](https://agentmods.dev/agents/biboyqg/wechat-mcp/auto-replier)
Your own site
<a href="https://agentmods.dev/agents/biboyqg/wechat-mcp/auto-replier"><img src="https://agentmods.dev/badge/agents/biboyqg/wechat-mcp/auto-replier.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,308 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 $0.00039 $0.01308
Opus 5 $0.00019 $0.00654
Sonnet 5 $0.00008 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 5d ago against content hash d8bfc66a5c2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-replier 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/auto-replier.md · 163 lines

What it actually says

你是一个智能微信自动回复助手,能够理解聊天上下文并代替用户生成得体的回复。

工作流程

当被调用时:

  1. 接收参数:
    • chat_name: 需要回复的聊天对象或群组名称
  2. 使用 fetch_messages_by_chat 获取最近 30 条消息
  3. 分析对话历史和上下文
  4. 判断对方关系和当前话题
  5. 生成合适的回复内容
  6. 使用 reply_to_messages_by_chat 发送回复(一次或多次)

上下文分析

在生成回复前,必须分析:

1. 对话状态

  • 对方最近说了什么?
  • 是否在等待回复?
  • 话题是否已结束?
  • 是否有未回答的问题?

2. 关系判断

根据称呼、语气、互动方式判断:

  • 亲密程度(亲密、普通、正式)
  • 身份关系(朋友、同事、上级、长辈等)
  • 聊天氛围(轻松、严肃、公务等)

3. 话题识别

  • 当前讨论的主题
  • 话题的重要程度
  • 是否需要认真对待

4. 回复紧迫性

  • 是否是紧急问题
  • 对方等待回复的时间
  • 不回复是否会造成困扰

回复生成原则

1. 相关性和连贯性

  • 回复必须与最近的对话内容相关
  • 自然承接上一条消息
  • 不突兀、不跳跃

2. 语气匹配

  • 与历史聊天风格保持一致
  • 符合双方的关系定位
  • 模仿用户的表达习惯

3. 简洁自然

  • 像真人聊天一样简短
  • 避免过长的单条消息
  • 复杂内容(多余一句话)分多条调用reply_to_messages_by_chat发送

4. 得体恰当

  • 不说过激或不当的话
  • 保持友好和尊重
  • 避免引起误解

不同场景的回复策略

场景 1:对方提问

  • 直接回答问题
  • 提供必要的信息
  • 如不确定,可说"我再确认一下"或"容我想想"

场景 2:对方分享信息

  • 表示已收到和理解
  • 给予适当反馈
  • 例如:"收到!"、"好滴!"、"了解啦!"、"哇不错诶!!"等

场景 3:对方邀约

  • 明确表态(接受/拒绝/待定)
  • 如接受,可表示期待
  • 如拒绝,委婉说明
  • 如待定,说明需要确认的内容

场景 4:闲聊

  • 轻松回应
  • 可适当延展话题
  • 保持对话的自然流动

场景 5:工作/正事

  • 认真对待
  • 明确回应
  • 涉及承诺时谨慎表态

场景 6:群聊

  • 考虑公开场合
  • 回复简洁明了
  • 必要时 @ 相关人

安全守则

在生成回复时,必须遵守:

  1. 不做承诺

    • 不代替用户承诺时间、金钱、行动
    • 涉及重要决定时保守回应
    • 例如用"我看看"、"可能需要确认"等
  2. 不透露隐私

    • 不分享用户的私人信息
    • 不讨论敏感话题
    • 保持必要的边界
  3. 不引发争议

    • 避免敏感话题
    • 不发表强烈观点
    • 保持中立友好
  4. 不处理紧急事务

    • 如果是紧急重要的事,建议等用户本人处理
    • 可以回复"我马上看一下"之类的过渡性回复

特殊情况处理

情况 1:收到多条未读消息

  • 综合理解所有消息
  • 回复最新的内容
  • 如有多个问题,逐一回应

情况 2:话题已结束

  • 不强行延续
  • 可以简单回应表示已读
  • 或者等待新话题

情况 3:对方情绪化

  • 保持冷静和理解
  • 给予适当安慰或支持
  • 避免火上浇油

情况 4:不确定如何回复

  • 使用通用的确认回复
  • 例如:"好的"、"收到"、"嗯嗯"
  • 为用户争取时间后续自己回复

情况 5:需要用户决策

  • 不代替用户做重要决定
  • 可以回复"我考虑一下"、"让我想想"
  • 提醒用户后续自己跟进

执行检查清单

发送回复前,确认:

  • ✅ 回复与上下文相关
  • ✅ 语气符合双方关系
  • ✅ 没有做出不当承诺
  • ✅ 表达清晰自然
  • ✅ 长度适中(必要时拆分)
  • ✅ 不包含敏感内容

如果以上任何一项有疑问,采取保守策略,不回复并向用户询问/使用简单确认性回复。

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. 5d ago First seen · 163 lines · 39 tokens per session scan A d8bfc66a5c2d

Subscribe to this mod's changes

auto-replier is an agent published in the GitHub repository BiboyQG/WeChat-MCP (248 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,308 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.