Clash Routes logo

Clash Routes

Community
majiayu000
clash-routes

查看本机进程的 Mihomo 实时代理链。当用户问 Claude、Codex、Gemini、ChatGPT、 浏览器或其他进程走哪个代理时使用。只读。Profile 拓扑和写入使用 clash-doctor, 出口 IP 质量使用 ip-check。

Overview

Publishermajiayu000
Repositoryspellbook
Skill nameclash-routes
Stars
280
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by majiayu000 on GitHub. Read the source before you install it.

Installation

Install the Clash Routes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/majiayu000/spellbook.git /tmp/spellbook
mkdir -p .claude/skills
cp -r /tmp/spellbook/skills/clash-routes .claude/skills/clash-routes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Clash Routes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Clash Routes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Clash Routes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Clash 线路查看工具

查看本机当前活跃连接,确认指定进程命中的规则、策略组与真实出口。不接受 SSH 参数;远程机器应先通过 Tailscale SSH 登录,再在目标机器执行同一只读流程。

用户传入的参数:$ARGUMENTS。没有参数时列出所有活跃连接。诊断 Gemini、ChatGPT 或浏览器流量时,先不加过滤获取实际 metadata.process,再使用观察到的进程名;不要假定它们属于 claude

获取凭证

读取 Clash Verge 配置,但不要打印 secret:

bash
SECRET=$(grep '^secret:' "$HOME/Library/Application Support/io.github.clash-verge-rev.clash-verge-rev/clash-verge.yaml" 2>/dev/null | awk '{print $2}')
[ -z "$SECRET" ] && SECRET=$(grep '^secret:' "$HOME/.config/clash/config.yaml" 2>/dev/null | awk '{print $2}')
[ -n "$SECRET" ] && echo "API secret: configured" || echo "API secret: not configured"

查询与回退

请求成功才采用该 endpoint。/tmp socket 存在但失效时继续尝试 /var/tmp,最后尝试配置的 HTTP controller。所有 endpoint 都失败时明确报错,不返回空数据。

bash
request_connections() {
  for socket_path in \
    /tmp/verge/verge-mihomo.sock \
    /var/tmp/verge/verge-mihomo.sock
  do
    [ -S "$socket_path" ] || continue
    if curl --fail --silent --show-error \
      --unix-socket "$socket_path" \
      "http://localhost/connections" \
      -H "Authorization: Bearer $SECRET"
    then
      return 0
    fi
  done

  controller=$(grep '^external-controller:' "$HOME/Library/Application Support/io.github.clash-verge-rev.clash-verge-rev/clash-verge.yaml" 2>/dev/null | awk '{print $2}' | tr -d "'\"")
  [ -n "$controller" ] || controller="127.0.0.1:9090"
  curl --fail --silent --show-error \
    "http://$controller/connections" \
    -H "Authorization: Bearer $SECRET"
}

if ! DATA=$(request_connections); then
  echo "无法从 Mihomo Unix socket 或 HTTP controller 获取连接数据" >&2
  exit 1
fi

if ! printf '%s' "$DATA" | python3 -c 'import json, sys; value=json.load(sys.stdin); assert isinstance(value.get("connections"), list)' 2>/dev/null; then
  echo "Mihomo 返回了无效的 connections JSON" >&2
  exit 1
fi

解析并展示

通过环境变量传递过滤值,避免把用户输入插进 Python 源码:

bash
printf '%s' "$DATA" | FILTER="$ARGUMENTS" python3 -c '
import json
import os
import sys
from collections import defaultdict

data = json.load(sys.stdin)
process_filter = os.environ.get("FILTER", "").strip().lower()
results = []

for connection in data.get("connections", []):
    metadata = connection.get("metadata", {})
    process = metadata.get("process", "unknown")
    if process_filter and process_filter not in process.lower():
        continue
    host = metadata.get("host", "") or metadata.get("destinationIP", "")
    port = metadata.get("destinationPort", "")
    rule = connection.get("rule", "")
    payload = connection.get("rulePayload", "")
    if payload:
        rule += "/" + payload
    chains = connection.get("chains", [])
    chain_text = " → ".join(reversed(chains)) if chains else "DIRECT"
    results.append({
        "process": process,
        "host": f"{host}:{port}" if port else host,
        "rule": rule,
        "chain": chain_text,
    })

grouped = defaultdict(list)
for result in results:
    grouped[result["process"]].append(result)

if not grouped:
    target = process_filter or "任何进程"
    print(f"未找到 {target} 的活跃连接")
    raise SystemExit(0)

for process, connections in sorted(grouped.items()):
    print(f"\n进程: {process} ({len(connections)} 个连接)")
    route_stats = defaultdict(lambda: {"count": 0, "hosts": set()})
    for connection in connections:
        key = "{} → {}".format(connection["rule"], connection["chain"])
        route_stats[key]["count"] += 1
        route_stats[key]["hosts"].add(connection["host"])
    for route, info in sorted(route_stats.items(), key=lambda item: -item[1]["count"]):
        hosts = sorted(info["hosts"])
        shown = ", ".join(hosts[:5])
        suffix = f" ... (+{len(hosts) - 5})" if len(hosts) > 5 else ""
        print(f"  线路: {route}")
        print("  连接数: {}".format(info["count"]))
        print(f"  目标: {shown}{suffix}")
'

解释结果

  • chains[-1] 是命中的策略组,chains[0] 是真实出口;展示时反转为“策略组 → 出口”。
  • Claude 常见进程是 claudeClaude Helper;Codex CLI 常见进程是 codex
  • Gemini CLI、ChatGPT 桌面端和浏览器的进程名以未过滤连接表为准。
  • Host 只有裸 IP 时,检查 sniffer.parse-pure-ip 和系统 DNS 是否绕过 Clash,不要直接改 AI 策略组。
  • 当前 profile 不是预期 Hub,或出口仍是原始订阅节点时,报告 drift;本 skill 不修改 YAML。

完成条件

  • 至少一个 Mihomo endpoint 返回合法 connections JSON。
  • 输出明确显示进程、规则、策略组和出口,或明确说明目标进程当前没有活跃连接。
  • 全程只读且没有打印 API secret。

Frequently asked questions

What does the Clash Routes AI skill do?

查看本机进程的 Mihomo 实时代理链。当用户问 Claude、Codex、Gemini、ChatGPT、 浏览器或其他进程走哪个代理时使用。只读。Profile 拓扑和写入使用 clash-doctor, 出口 IP 质量使用 ip-check。

Why use Clash Routes on TypingMind?

Because you install it once and use it with any model. Clash Routes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Clash Routes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/majiayu000/spellbook/tree/main/skills/clash-routes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Clash Routes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Clash Routes?

As many as you like. As long as a model supports skills, you can use Clash Routes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Clash Routes AI skill free?

Yes. It is published on GitHub by majiayu000 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇