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 samttoo22-MewCat/OpenSoul --skill web-researchgit clone --depth 1 https://github.com/samttoo22-MewCat/OpenSoulWrote 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/samttoo22-mewcat/opensoul/web-research)<a href="https://agentmods.dev/skills/samttoo22-mewcat/opensoul/web-research"><img src="https://agentmods.dev/badge/skills/samttoo22-mewcat/opensoul/web-research/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/samttoo22-mewcat/opensoul/web-research"><img src="https://agentmods.dev/badge/skills/samttoo22-mewcat/opensoul/web-research.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 | $0.00103 | $0.01027 |
| Opus 5 | $0.00051 | $0.00513 |
| Sonnet 5 | $0.00021 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
web-research scanned grade A with 0 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 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research（SearXNG + Jina Reader）
輕量網頁研究工具，結合兩個元件：
| 元件 | 用途 | 端點 |
|---|---|---|
| SearXNG（本地） | 隱私搜尋，聚合 Google / Bing / DDG 等 | http://localhost:8888 |
| Jina Reader | 將任意 URL 轉成乾淨 Markdown，無須瀏覽器 | https://r.jina.ai/<url> |
何時使用
- 需要搜尋最新資訊、新聞、技術文件 → 用
research或search - 需要讀取某個網頁的全文內容 → 用
fetch - 優先選擇此工具取代
browser-control；只有在需要登入、互動操作或 JS 渲染時才改用瀏覽器
前置需求
SearXNG 須在 Docker 內運行：
docker compose -f openclaw/docker-compose.yml up searxng -d
Jina Reader 為雲端服務，不需額外設定。
指令
1. 搜尋（search）
python scripts/web_research.py --action search --query "Claude AI 2025"
python scripts/web_research.py --action search --query "台灣 AI 新創" --language "zh-TW" --max-results 10
python scripts/web_research.py --action search --query "Python asyncio" --categories "it"
python scripts/web_research.py --action search --query "openai" --json
2. 抓取單頁（fetch）
python scripts/web_research.py --action fetch --url "https://example.com"
python scripts/web_research.py --action fetch --url "https://news.ycombinator.com" --timeout 20
python scripts/web_research.py --action fetch --url "https://example.com" --json
3. 搜尋 + 自動抓取全文（research）
# 搜尋並抓取前 3 筆結果全文（預設）
python scripts/web_research.py --action research --query "AI agent security 2025"
# 抓取前 5 筆
python scripts/web_research.py --action research --query "LangChain tutorial" --fetch-top 5
# 中文搜尋
python scripts/web_research.py --action research --query "生成式 AI 應用" --language "zh-TW" --fetch-top 2
參數一覽
| 參數 | 預設 | 說明 |
|---|---|---|
--action |
必填 | search / fetch / research |
--query / -q |
— | 搜尋關鍵字 |
--url / -u |
— | 目標 URL（fetch 用） |
--categories / -c |
general |
general, news, it, science, images, videos, social media |
--language / -l |
en-US |
語言代碼 |
--max-results / -n |
5 |
搜尋結果數量上限 |
--fetch-top |
3 |
research 模式抓取前幾筆完整內容 |
--timeout |
15 |
Jina Reader 逾時秒數 |
--json |
off | 輸出原始 JSON |
What ships with it
1 file 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 · 97 lines · 103 tokens per session scan A e3354cecbe00
web-research is a skill published in the GitHub repository samttoo22-MewCat/OpenSoul (19 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 1,027 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Discord Integration
Send messages to Discord channels via webhook or bot.
twitter-writer
Write X/Twitter posts, tweet drafts, shitposts, and short threads for engineering or startup topics. Use this when the user asks for a tweet, X post, shitpost, post draft, or wants social copy for Twitter/X. Always return 3 distinct variants, each inside its own code block, unless the user explicitly asks for one.
obsidian-pro
Advanced Obsidian knowledge management using callouts, properties, and wikilinks. Aligned with the Gold Standard.
Weather
Get current weather and forecasts using wttr.in (no API key needed).
vault-memory
Treat the Obsidian vault as operational memory, not just note storage. Focus on retrieval quality, metadata integrity, and safe consolidation.
Logging
Where logs live and when to write them — errors, daily, system.