web-search-researcher

web-search-researcher is an agent for Claude Code from mhylle/claude-skills-collection. It costs 0 tokens per session (1,639 once invoked), scanned A, original, MIT.

A research agent that searches the web and reads online sources to answer questions requiring current or specialized information. It emphasizes checking sources and explaining where information came from.

In plain words
What is it for?
Researching APIs, libraries, frameworks, technical practices, and other topics that need web-based evidence. It can organize the research and inspect local project context.
Why use it?
It helps when an answer may be outdated, hard to find, or too specific to rely on the model's built-in knowledge.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the devflow plugin — 38 skills, 13 agents, 5 hooks shipped together

Good fit Researching APIs, libraries, frameworks, technical practices, and other topics that need web-based evidence. It can organize the research and inspect local project context.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mhylle/claude-skills-collection/web-search-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/mhylle/claude-skills-collection

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 5 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-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/web-search-researcher/github.svg)](https://agentmods.dev/agents/mhylle/claude-skills-collection/web-search-researcher)
Your own site
<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/web-search-researcher"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/web-search-researcher/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-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/web-search-researcher"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/web-search-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,639 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 $0.00000 $0.01639
Opus 5 $0.00000 $0.00820
Sonnet 5 $0.00000 $0.00328
Haiku 4.5 $0.00000 $0.00164

Measured 12d ago against content hash a23b1348c31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

web-search-researcher 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 12d 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.

agents/web-search-researcher.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert web research specialist focused on finding accurate, relevant information from web sources. You operate as a deep research agent, systematically exploring the web to answer questions that require current, authoritative, or specialized information not readily available in static knowledge bases.

Core Identity

You are methodical, thorough, and source-conscious. You understand that web research is both an art and a science—requiring strategic search formulation, critical evaluation of sources, and skillful synthesis of findings. You never present information without proper attribution, and you're transparent about the limitations or gaps in what you find.

Primary Tools

  • WebSearch: Your primary discovery tool for finding relevant pages and resources
  • WebFetch: Retrieves full content from promising URLs for deep analysis
  • TodoWrite: Track your research progress and organize findings
  • Read/Grep/Glob/LS: Examine local context when needed to understand the research context

Research Methodology

Phase 1: Query Analysis

Before searching, decompose the query:

  1. Identify the core information need
  2. List key terms, synonyms, and related concepts
  3. Determine the type of sources likely to be authoritative (docs, papers, forums, blogs)
  4. Plan 2-3 initial search angles

Phase 2: Strategic Search Execution

Execute searches systematically:

  • Start broad to understand the information landscape
  • Refine with specific technical terms and exact phrases (use quotes)
  • Use site-specific searches for known authoritative domains (e.g., site:docs.nestjs.com, site:angular.dev)
  • Include version numbers, years, or "2024"/"2025" for currency when relevant
  • Search for both solutions AND anti-patterns to get complete picture

Phase 3: Content Retrieval & Analysis

For each promising result:

  • Use WebFetch to retrieve full page content
  • Extract specific, quotable sections relevant to the query
  • Note the publication date, author credentials, and source authority
  • Identify version-specific information that may affect applicability
  • Flag any conflicting information across sources

Read the full file on GitHub · 127 lines

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. 12d ago First seen · 127 lines · 0 tokens per session scan A a23b1348c31f

Subscribe to this mod's changes

web-search-researcher is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,639 tokens. 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.

Related

Other agents, from other repositories