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 phanghonghao/THU-Awesome-Skills --skill web-search-fallbackgit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-SkillsWrote 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/phanghonghao/thu-awesome-skills/web-search-fallback)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/web-search-fallback"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/web-search-fallback/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/phanghonghao/thu-awesome-skills/web-search-fallback"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/web-search-fallback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00123 | $0.03230 |
| Opus 5 | $0.00062 | $0.01615 |
| Sonnet 5 | $0.00025 | $0.00646 |
| Haiku 4.5 | $0.00012 | $0.00323 |
Grade C, and why
web-search-fallback scanned grade C with 2 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 11d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL --max-time 25 "http://export.arxiv.org/api/query?search_query=all:KEYWORD1+AND+all:KEYWORD2&start=0&max_results=10&sortBy=submittedDate&sortOrder=descending" | python -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
GitHub API (gh CLI / curl), Semantic Scholar API, and direct curl page fetch. How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search Fallback — 零 MCP 额度的本地搜索/阅读
当 MCP web_search / webReader 工具返回 429 限流错误(MCP error -429 / Weekly/Monthly Limit Exhausted)时,立即切换到本 skill 的本地方案,不要重试 MCP。
也适用于:用户主动要求搜论文、搜 GitHub、读网页,且不想消耗 MCP 额度时。
路由决策表
| 用户意图 | 路由 | 工具 |
|---|---|---|
| 搜学术论文 | Route 1: arXiv API | curl + python XML 解析 |
| 搜 GitHub 仓库 | Route 2: GitHub API | gh search repos 或 curl REST API |
| 论文引用/关联图谱 | Route 3: Semantic Scholar | curl JSON API |
| 读特定 URL 内容 | Route 4: 直接 curl 抓取 | curl -sL + 文本提取 |
| 读知乎专栏文章 | Route 4b: 知乎 / Jina Reader | curl https://r.jina.ai/<url> |
| 通用网络搜索 | Route 5: DuckDuckGo HTML | curl + grep(兜底,质量有限) |
Windows 注意: 用 python 而非 python3(Windows App Execution Alias 会拦截 python3)。
Route 1: arXiv API(学术论文搜索)
基础搜索
curl -sL --max-time 25 "http://export.arxiv.org/api/query?search_query=all:KEYWORD1+AND+all:KEYWORD2&start=0&max_results=10&sortBy=submittedDate&sortOrder=descending" | python -c "
import sys,xml.etree.ElementTree as ET
ns={'a':'http://www.w3.org/2005/Atom'}
root=ET.parse(sys.stdin).getroot()
for e in root.findall('a:entry',ns):
t=e.find('a:title',ns).text.strip().replace('\n',' ')
d=e.find('a:published',ns).text[:10]
aid=e.find('a:id',ns).text.split('/')[-1]
s=e.find('a:summary',ns).text.strip().replace('\n',' ')[:200]
print(f'{d} | {aid} | {t}')
print(f' {s}...')
print()
"
搜索语法
all:keyword— 全文搜索ti:keyword— 仅标题au:keyword— 仅作者- 布尔:
+AND+,+OR+,+AND+NOT+ - 精确短语:
%22reward+design%22(URL 编码的引号) - 排序:
sortBy=submittedDate|relevance|lastUpdatedDate&sortOrder=ascending|descending
示例:搜 reward design + LLM
curl -sL --max-time 25 "http://export.arxiv.org/api/query?search_query=all:%22reward+design%22+AND+all:%22large+language+model%22&max_results=12&sortBy=submittedDate&sortOrder=descending"
按 arxiv ID 取全文摘要
curl -sL --max-time 25 "http://export.arxiv.org/api/query?id_list=2310.12931" | python -c "
import sys,xml.etree.ElementTree as ET
ns={'a':'http://www.w3.org/2005/Atom'}
root=ET.parse(sys.stdin).getroot()
e=root.find('a:entry',ns)
print(e.find('a:title',ns).text.strip())
print(e.find('a:summary',ns).text.strip())
"
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.
- 11d ago First seen · 284 lines · 123 tokens per session scan C 47d8abb6d7be
web-search-fallback is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 3,230 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…