Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/id5463/mcp-server-researchnpx agentmods add skills/id5463/mcp-server-research/deepsearchWrote 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/deepsearch)<a href="https://agentmods.dev/skills/id5463/mcp-server-research/deepsearch"><img src="https://agentmods.dev/badge/skills/id5463/mcp-server-research/deepsearch.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 | $0.00034 | $0.04394 |
| Opus 5 | $0.00017 | $0.02197 |
| Sonnet 5 | $0.00007 | $0.00879 |
| Haiku 4.5 | $0.00003 | $0.00439 |
Grade A, and why
deepsearch 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.
- `curl` 可用(用于抓取网页全文) How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSearch — 深度搜索研究技能
模仿 OpenAI Deep Research 的工作方式,对复杂问题进行多步自主研究与综合。
核心原理
- 将用户问题拆解为多个子课题
- 对每个子课题进行多轮搜索(Web + 本地知识库双渠道)
- 选择最有价值的来源并读取全文
- 从多个角度交叉验证关键事实
- 综合所有信息生成结构化报告,附引用来源
数据源
DeepSearch 支持多数据源搜索:
| 数据源 | 适用场景 | 访问方式 |
|---|---|---|
| DuckDuckGo Web | 通用互联网信息 | ddgs Python 包 |
| DuckDuckGo News | 最新动态与新闻 | ddgs.news() |
| AnythingLLM 本地 KB | 私有文档、内部知识、专业领域 | MCP 工具或 REST API |
详情见 references/anythingllm-integration.md。
前置条件
Web 搜索
- duckduckgo-search 技能已安装
- Python
ddgs包已安装(pip install ddgs) curl可用(用于抓取网页全文)
注意:在 Windows 上,ddgs CLI 可能存在连接问题,优先使用 Python API 方式。
本地知识库(AnythingLLM,可选)
- AnythingLLM 运行在
http://localhost:8899 - API Key 已生成(在 anything-llm 技能中)
- Hermes 重启后可用
mcp_anythingllm_*工具;或直接用 REST API 降级 - 详情见
references/anythingllm-integration.md
运行时陷阱(首次使用前必读)
陷阱 1:execute_code 沙箱没有 ddgs
execute_code(hermes_tools)中的 Python 是一个隔离沙箱,不包含 ddgs 包。
即使终端里已安装,沙箱也无法导入。
正确做法:始终通过 terminal 工具运行 Python 搜索代码,不要用 execute_code。
陷阱 2:-c 标志被审批系统拦截
terminal 会检测 python -c "..." 或管道到 Python 的模式,弹出「需要用户批准」对话框。
正确做法:写 .py 脚本文件,再用 terminal 执行。
write_file -> 将 Python 搜索代码写入临时脚本
terminal -> python <脚本路径>
陷阱 3:Windows 上 Python 路径可能不对
在 Windows git-bash 中,python 可能指向 Hermes venv (3.11) 而非安装了 ddgs 的系统 Python (3.13)。
如果 from ddgs import DDGS 报错,先检查:
where python
python --version
"C:/Users/a/AppData/Local/Programs/Python/Python313/python.exe" -c "from ddgs import DDGS; print('ok')"
陷阱 5:来源标注不能后补
每个搜索步骤返回的结果(标题、URL、摘要)必须立即记录到报告草稿中。不要在 Step 6 再翻回去找来源 URL。每轮搜索后:
# 每轮搜索后立即记录
## 轮次 N 搜索结果
- [数据点] -> 来源: <URL>
- [数据点] -> 来源: <URL>
这样最终报告才有充分的粒度引用来源。
陷阱 6:不要一次性规划所有搜索,要迭代
WebWatcher 风格的迭代式搜索更有效:每步搜索后先读结果,根据已收集的信息决定下一步搜什么,而不是一开始就把所有子问题都搜完。
陷阱 7:先检查已有安装和技能参考,不要克隆/安装已有工具
在开始任何研究或集成任务之前,必须按顺序做:
- 加载相关技能 — 先用
skill_view()读取涉及的所有技能的 SKILL.md 和references/文件 - 检查技能参考文件 — 看
references/目录下已有的文档是否已经涵盖了你打算做的事情 - 检查系统已安装 — 通过
python -c "import ..."或which ...验证工具是否已在系统上,而不是直接 git clone 或 pip install
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.
- 7d ago First seen · 418 lines · 34 tokens per session scan A 79fdb801dd61
deepsearch is a skill published in the GitHub repository id5463/mcp-server-research (0 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 4,394 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…