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 id5463/mcp-server-research --skill research-toolkitgit clone --depth 1 https://github.com/id5463/mcp-server-researchWrote 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/id5463/mcp-server-research/research-toolkit)<a href="https://agentmods.dev/skills/id5463/mcp-server-research/research-toolkit"><img src="https://agentmods.dev/badge/skills/id5463/mcp-server-research/research-toolkit/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/id5463/mcp-server-research/research-toolkit"><img src="https://agentmods.dev/badge/skills/id5463/mcp-server-research/research-toolkit.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 | $0.00029 | $0.00746 |
| Opus 5 | $0.00015 | $0.00373 |
| Sonnet 5 | $0.00006 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
research-toolkit 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 需要下载**JS 渲染的页面**(React/Vue/Next.js SPA,普通 curl 拿不到内容) What it actually says
research-toolkit
通用研究工具包:网页搜索 + 无头浏览器下载。
何时使用
- 需要搜索网页/新闻/图片来找链接或信息时
- 需要下载JS 渲染的页面(React/Vue/Next.js SPA,普通 curl 拿不到内容)
- 遇到 CDN 反爬(Akamai / CloudFront / Cloudflare),curl 返回 Access Denied
- 需要下载 PDF,但服务器拦截非浏览器请求
工具
ddgs_search.py — DuckDuckGo 搜索
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\ddgs_search.py" <cmd> <query> [options]
子命令: text | images | news | videos
常用参数: --max N --region wt-wt --timelimit d|w|m|y -o json|csv
示例:
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\ddgs_search.py" text "site:sec.gov Block Inc 10-K" --max 10
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\ddgs_search.py" news "CFPB enforcement action" --timelimit m
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\ddgs_search.py" text "query" -o json --max 5
headless_dl.py — Headless Chrome 下载器
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\headless_dl.py" <url> <output> [--mode text|html|pdf] [--wait "text"] [--timeout 30]
模式:
--mode text— 提取 innerText 纯文本(过滤导航/CSS/JS)--mode html— 保存完整渲染后的 HTML DOM--mode pdf— 通过 Chrome CDP 下载 PDF(绕过 CDN 反爬)
示例:
# 等页面出现 "Annual Report" 后再截取文本
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\headless_dl.py" "https://spa.example.com" out.txt --mode text --wait "Annual Report"
# 绕过 Akamai 下载 PDF
python "C:\Users\a\.agents\skills\research\research-toolkit\scripts\headless_dl.py" "https://cdn.gov/doc.pdf" out.pdf --mode pdf --timeout 60
典型工作流
- 用
ddgs_search.py搜索目标链接 - 用
headless_dl.py下载 JS 渲染页面或 PDF - 对 PDF 做 OCR / 对文本做分析
依赖
pip install -r "C:\Users\a\.agents\skills\research\research-toolkit\scripts\requirements.txt"
需要 Chrome 浏览器。
许可
MIT
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 29 tokens per session scan A b19e458b3815
research-toolkit is a skill published in the GitHub repository id5463/mcp-server-research (0 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 746 once invoked, about $0.0001 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 2026-08-31.
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…