web_search

web_search is a skill for Claude Code from bayeslabs-rsi/Svatah. It costs 13 tokens per session (248 once invoked), scanned A, original, Apache-2.0.

A web-search helper for finding information about a current experiment or unfamiliar technical problem. It uses Tavily when configured, or DuckDuckGo as a fallback, and returns search results with sources.

In plain words
What is it for?
Researching technical best practices, investigating unfamiliar errors or library behavior, and finding current approaches during experiment research or optimization. Sources should be cited in experiment notes.
Why use it?
An experiment may depend on current practices, recent techniques, or behavior that is not covered by local knowledge. Searching gives the people running it outside evidence to inform their hypotheses.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the sva plugin — 6 skills, 3 hooks shipped together

Good fit Researching technical best practices, investigating unfamiliar errors or library behavior, and finding current approaches during experiment research or optimization. Sources should be cited in experiment notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bayeslabs-rsi/svatah/web_search
Install

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.

Any agent
npx skills add bayeslabs-rsi/Svatah --skill web_search
Clone the repo
git clone --depth 1 https://github.com/bayeslabs-rsi/Svatah

Made for: Claude Code.

Or install sva, the plugin that ships this one along with the rest of its 6 skills, 3 hooks.

Wrote 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.

agentmods badge for web_search

README.md
[![agentmods](https://agentmods.dev/badge/skills/bayeslabs-rsi/svatah/web_search/github.svg)](https://agentmods.dev/skills/bayeslabs-rsi/svatah/web_search)
Your own site
<a href="https://agentmods.dev/skills/bayeslabs-rsi/svatah/web_search"><img src="https://agentmods.dev/badge/skills/bayeslabs-rsi/svatah/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.

agentmods 80×15 button for web_search

Your own site · 80×15
<a href="https://agentmods.dev/skills/bayeslabs-rsi/svatah/web_search"><img src="https://agentmods.dev/badge/skills/bayeslabs-rsi/svatah/web_search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.00248
Opus 5 $0.00006 $0.00124
Sonnet 5 $0.00003 $0.00050
Haiku 4.5 $0.00001 $0.00025

Measured 11d ago against content hash 774b5c6f45f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d 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.

plugins/sva/skills/web_search/SKILL.md · 33 lines

What it actually says

Web Search Skill

Purpose

Search the web to find information, best practices, latest techniques, and solutions relevant to the current optimization experiment.

When to Use

  • During /sva:research to understand best practices and latest methods for the target domain
  • During /sva:optimize when subagents need external knowledge to form better hypotheses
  • When encountering unfamiliar error patterns or library behaviors
  • When looking for state-of-the-art approaches to beat the current frontier

How to Use

Run:

python -c "from sva.web_search import search; import json; print(json.dumps(search('{QUERY}', max_results=5), indent=2))"

Replace {QUERY} with your search query. Results include title, URL, and snippet.

If TAVILY_API_KEY is set, the skill uses Tavily. Otherwise it falls back to DuckDuckGo.

Rules

  • Keep queries specific and technical
  • Use results to inform hypotheses, not to copy-paste code blindly
  • Always cite sources in experiment annotations
Changes

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.

  1. 11d ago First seen · 33 lines · 13 tokens per session scan A 774b5c6f45f9

Subscribe to this mod's changes

web_search is a skill published in the GitHub repository bayeslabs-rsi/Svatah (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 248 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

auto-paper-improvement-loop

An automated loop for improving a generated research paper through repeated review, editing, and recompilation. Recompiling rebuilds the paper so changes can be checked in the final document.

AI4Scientist/nano-scientist · 67 tokens

proof-checker

A rigorous proof-checking and repair skill for LaTeX mathematics. LaTeX is a text format commonly used to write mathematical documents.

AI4Scientist/nano-scientist · 90 tokens

citation-audit

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context…

AI4Scientist/nano-scientist · 114 tokens

grant-proposal

A grant-writing workflow that turns research ideas and related literature into structured funding proposals for named national and international grant formats.

AI4Scientist/nano-scientist · 131 tokens

paper-illustration

A tool for creating academic-paper illustrations such as architecture diagrams and method figures with Gemini image generation and Claude-guided revisions.

AI4Scientist/nano-scientist · 67 tokens

paper-navigator

Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA), and read with structured analysis (3-level strategy). Use when: finding papers, reading a paper, related work, citation…

AI4Scientist/nano-scientist · 141 tokens