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.
npx skills add majiayu000/spellbook --skill clash-routesgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/skills/majiayu000/spellbook/clash-routes)<a href="https://agentmods.dev/skills/majiayu000/spellbook/clash-routes"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/clash-routes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/spellbook/clash-routes"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/clash-routes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 50 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00067 | $0.01438 |
| Opus 5 | $0.00034 | $0.00719 |
| Sonnet 5 | $0.00013 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
clash-routes scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
if curl --fail --silent --show-error \ How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clash 线路查看工具
查看本机当前活跃连接,确认指定进程命中的规则、策略组与真实出口。不接受 SSH 参数;远程机器应先通过 Tailscale SSH 登录,再在目标机器执行同一只读流程。
用户传入的参数:$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:
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。
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' "$DATA" | python3 -c 'import json, sys; value=json.load(sys.stdin); assert isinstance(value.get("connections"), list)' 2>/dev/null; then
echo "Mihomo 返回了无效的 connections JSON" >&2
exit 1
fi
解析并展示
通过环境变量传递过滤值,避免把用户输入插进 Python 源码:
printf '%s' "$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}")
'
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.
- 7d ago Changed · -67 lines · +12 tokens per session 04c9aadc1807
- 11d ago First seen · 207 lines · 55 tokens per session scan A d90cf2edb93e
clash-routes is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,438 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.