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 AbdullahMalik17/malikclaw --skill web-searchgit clone --depth 1 https://github.com/AbdullahMalik17/malikclawWrote 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/abdullahmalik17/malikclaw/web-search)<a href="https://agentmods.dev/skills/abdullahmalik17/malikclaw/web-search"><img src="https://agentmods.dev/badge/skills/abdullahmalik17/malikclaw/web-search/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/abdullahmalik17/malikclaw/web-search"><img src="https://agentmods.dev/badge/skills/abdullahmalik17/malikclaw/web-search.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00216 |
| Opus 5.5 | $0.00012 | $0.00086 |
| Sonnet 5.5 | $0.00006 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
web-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 1mo 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.
What it actually says
🔍 Web Search & Context Retrieval Skill
Use this skill when fetching live information from the web, researching recent events, or verifying facts.
Supported Providers
- DuckDuckGo: Default free search provider.
- Tavily: Optimized for AI agent search and content extraction.
- Brave Search: Fast, independent web search API.
- Perplexity: LLM-augmented deep research search.
- SearXNG: Privacy-respecting meta-search engine.
Usage Example
{
"query": "Go 1.22 memory allocation optimizations",
"max_results": 5
}
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.
- 1mo ago First seen · 29 lines · 31 tokens per session scan A 35af79466b9a
web-search is a skill published in the GitHub repository AbdullahMalik17/malikclaw (19 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 216 once invoked, about $0.0001 per session on Opus 5.5. 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
web-search-plus
Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), Perplexity (AI Answers), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.
web-search-plus
Search the web and extract URLs with routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, You.com, SearXNG, SerpBase, and Keenable. Returns ranked sources and page text; supports freshness filters and research across providers.
multi-search-engine
Zero-config multi-engine search aggregating 17 search engines (8 Chinese + 9 international) without API keys.
tavily-search
Real-time web search using Tavily API - search the web, extract page content, and get up-to-date information for RAG and research tasks.
seek
Web Exploration & Grounding Doctrine. Classifies search intent, executes via arifroute, and enforces APEX/F12 provenance.
web-search-plus-zh
A web-search tool that connects one interface to several search providers, including Google-based search, research search, AI answers, and privacy-focused search. It chooses a provider based on the kind of question being asked.