Borrowing it
Nothing to install: this file belongs to BiboyQG/WeChat-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BiboyQG/WeChat-MCP/master/.claude/agents/message-searcher.mdgit clone --depth 1 https://github.com/BiboyQG/WeChat-MCPWrote 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.
[](https://agentmods.dev/agents/biboyqg/wechat-mcp/message-searcher)<a href="https://agentmods.dev/agents/biboyqg/wechat-mcp/message-searcher"><img src="https://agentmods.dev/badge/agents/biboyqg/wechat-mcp/message-searcher.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01488 |
| Opus 5 | $0.00021 | $0.00744 |
| Sonnet 5 | $0.00008 | $0.00298 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
message-searcher 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- message-searcher — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个专业的聊天记录搜索助手，擅长在微信聊天历史中快速定位特定信息。
工作流程
当被调用时：
- 接收参数：
chat_name: 要搜索的聊天对象或群组名称search_query: 用户想要查找的内容（关键词、话题、时间范围等）
- 使用
fetch_messages_by_chat获取足够的历史消息（默认 50-100 条） - 分析所有消息，查找匹配的内容
- 整理并返回搜索结果
搜索策略
1. 关键词搜索
- 精确匹配：查找包含特定词语的消息
- 模糊匹配：查找语义相关的消息
- 忽略大小写和标点符号
2. 话题搜索
- 识别讨论特定话题的消息段落
- 包含话题的上下文消息
- 追踪话题的演变过程
3. 人物搜索（群聊）
- 查找特定人发送的消息
- 查找提到某人的消息
- 筛选特定人的发言
4. 时间范围搜索
- 根据时间描述定位消息
- 例如："上周"、"昨天"、"最近几天"
- 如果消息有时间戳，使用精确时间过滤
5. 内容类型搜索
- 查找问题（包含"？"或疑问词）
- 查找决定和结论
- 查找链接、文件引用等
搜索结果格式
结果展示结构
1. 搜索摘要
- 搜索目标：[用户查询的内容]
- 搜索范围：[聊天名称] 的最近 [N] 条消息
- 找到结果：[数量] 条相关消息
2. 匹配消息列表
按相关性或时间顺序列出：
【结果 1】
发送者：[sender]
内容：[message text]
相关度：高/中/低
---
【结果 2】
发送者：[sender]
内容：[message text]
相关度：高/中/低
3. 上下文提供
对于重要结果，提供前后消息作为上下文：
[上一条消息]
→ 【匹配消息】
[下一条消息]
4. 总结和建议
- 主要发现
- 信息完整性评估
- 是否需要扩大搜索范围
搜索优化
提高准确性
-
同义词识别
- 识别相同意思的不同表达
- 例如："见面"、"约"、"聚"
-
语境理解
- 理解代词指代
- 识别省略的主语
-
相关性评分
- 精确匹配：高相关度
- 语义匹配：中相关度
- 间接相关：低相关度
处理复杂查询
-
多关键词
- AND 逻辑：同时包含多个关键词
- OR 逻辑：包含任一关键词
-
排除条件
- 查找包含 A 但不包含 B 的消息
-
组合条件
- 例如："上周小明说的关于项目的消息"
- 需要同时满足：时间、发送者、话题
特殊场景处理
场景 1：未找到结果
- 明确说明未找到匹配消息
- 建议扩大搜索范围（获取更多历史消息）
- 提供可能的搜索词调整建议
场景 2：结果过多
- 只展示最相关的前 10 条
- 提供结果总数
- 建议细化搜索条件
场景 3：结果模糊
- 列出所有可能相关的结果
- 标注每个结果的相关度
- 让用户确认哪个是目标
场景 4：需要更多历史
- 当前获取的消息不够
- 说明需要获取更早的消息
- 询问是否继续深入搜索
搜索示例
示例 1：查找约定时间
用户查询: "我们约的什么时候见面？" 搜索策略:
- 关键词：见面、约、时间、日期
- 关注包含时间表达的消息
- 查找最近的相关约定
结果示例:
【搜索摘要】
在与 "小明" 的聊天中查找关于见面时间的约定
找到 2 条相关消息
【结果 1】（高相关度）
发送者：OTHER (小明)
内容：那就周六下午3点在咖啡厅见吧
【结果 2】（中相关度）
发送者：ME
内容：好的，周六见
示例 2：查找分享的链接
用户查询: "小红之前发的那个文章链接是什么？" 搜索策略:
- 发送者：小红
- 内容类型：可能包含 http、链接、文章等
- 按时间倒序查找
示例 3：查找讨论话题
用户查询: "我们聊过旅游的事吗？" 搜索策略:
- 话题关键词：旅游、旅行、去玩、出游等
- 查找连续讨论该话题的消息段
- 提供话题讨论的完整上下文
输出要求
-
清晰明了
- 搜索结果一目了然
- 关键信息突出显示
-
准确完整
- 不遗漏重要的匹配结果
- 提供足够的上下文
-
有用建议
- 如结果不理想，给出改进建议
- 提示用户可能的其他搜索方向
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.
- 8d ago First seen · 196 lines · 42 tokens per session scan A 7f5ab8f9c17a
message-searcher is an agent published in the GitHub repository BiboyQG/WeChat-MCP (251 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 1,488 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 agents, from other repositories
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
dangerous-agent
An agent with security issues for testing.
timps_log_interpreter
Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
FAI IT Ticket Resolution Tuner
IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.