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 InternLM/WildClawBench --skill ddgs-searchgit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/ddgs-search)<a href="https://agentmods.dev/skills/internlm/wildclawbench/ddgs-search"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/ddgs-search.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.00838 |
| Opus 5 | $0.00036 | $0.00419 |
| Sonnet 5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
ddgs-search 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 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.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ddgs-search
Why This Skill?
🆓 Completely free — no API keys, no subscriptions, no rate limits, no billing surprises.
🔍 8 search engines in one — Google, Bing, DuckDuckGo, Brave, Yandex, Yahoo, Wikipedia, and Mojeek. Switch engines with a single flag. Most search skills only support one.
🎓 Built-in arXiv research search — search academic papers directly via arXiv's free API. Returns authors, categories, abstracts, and publication dates. Perfect for researchers, students, and AI/ML practitioners.
🔌 Drop-in replacement — outputs web-search-plus compatible JSON, so it works with any skill or tool that expects that format. Zero config migration.
⚡ Lightweight — single pip package, no browser automation, no headless Chrome. Searches complete in 1-3 seconds.
Install
python3 scripts/install.py
Works on macOS, Linux, and Windows. Installs the ddgs package, verifies CLI access, and runs a quick search test.
Manual install
pip install ddgs
Web Search
CLI wrapper (recommended)
The ddgs-search wrapper outputs clean JSON to stdout with no interactive prompts or abort issues:
# Google (default)
ddgs-search "your query" 5 google
# Other engines
ddgs-search "your query" 3 duckduckgo
ddgs-search "your query" 5 brave
ddgs-search "your query" 10 yandex
Python script (web-search-plus compatible JSON)
# Google (default)
python3 scripts/search.py -q "your query" -m 5
# Other engines
python3 scripts/search.py -q "your query" -b duckduckgo
python3 scripts/search.py -q "your query" -b brave
python3 scripts/search.py -q "your query" -b yandex
python3 scripts/search.py -q "your query" -b yahoo
python3 scripts/search.py -q "your query" -b wikipedia
Output (web-search-plus compatible JSON):
{
"provider": "ddgs",
"results": [
{"title": "...", "url": "...", "snippet": "...", "published_date": "..."}
]
}
arXiv Search
# Search by topic
python3 scripts/arxiv_search.py -q "3D gaussian splatting" -m 10
# Field-specific search (title, abstract, category)
python3 scripts/arxiv_search.py -q "ti:transformer AND cat:cs.CV" -m 5
# Sort by relevance instead of date
python3 scripts/arxiv_search.py -q "reinforcement learning" --sort-by relevance
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 · 103 lines · 71 tokens per session scan A 3492014df6e7
ddgs-search is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 21d ago), licensed MIT. It adds 71 tokens to every session and 838 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
naga-config
A configuration-management skill for Naga, including its settings, connected tools, and imported skills.
naga_control
A control interface for changing Naga’s own running state and settings through a specific agent type.
live2d_controller
// 读取：system.characterbundle.loadcharacterskillsections -> system.config.buildtier1variables.characterbuiltinskillsprompt.
file-manager
A file and folder management helper for organizing files on a computer.
travel-explore
You are a network explorer on a travel adventure. Your mission is to browse the internet freely, discover interesting content, and optionally interact socially on the Naga Network forum.