web-researcher

web-researcher is a skill for Claude Code, Codex from creatorpiyush/webmesh-mcp. It costs 72 tokens per session (406 once invoked), scanned A, original, MIT.

A web-research skill for investigating a website, its documentation, or its technology stack across multiple pages. It first maps useful links, then retrieves the full content of selected pages.

In plain words
What is it for?
Researching documentation, exploring site structure, investigating technologies, and collecting information from selected pages.
Why use it?
It keeps large research tasks organised and reduces the amount of irrelevant website content sent to the assistant.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Researching documentation, exploring site structure, investigating technologies, and collecting information from selected pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/creatorpiyush/webmesh-mcp/web-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.

Any agent
npx skills add creatorpiyush/webmesh-mcp --skill web-researcher
Clone the repo
git clone --depth 1 https://github.com/creatorpiyush/webmesh-mcp

Made for: Claude Code, Codex.

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-researcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-researcher/github.svg)](https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-researcher)
Your own site
<a href="https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-researcher"><img src="https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-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-researcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-researcher"><img src="https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 406 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 $0.00072 $0.00406
Opus 5 $0.00036 $0.00203
Sonnet 5 $0.00014 $0.00081
Haiku 4.5 $0.00007 $0.00041

Measured 10d ago against content hash 328d8e67ea1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

web-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 10d 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.

skills/web-researcher/SKILL.md · 40 lines

What it actually says

Web Researcher Skill

This skill guides AI agents on how to conduct deep, structured web research using webmesh-mcp tools with minimal token consumption.

Research Workflow Strategy

Phase 1: Discover Structure
   └── web_crawl (startUrl, maxDepth: 2, contentDepth: "summary")
       └── Collect page titles, link graph, and 200-char excerpts

Phase 2: Evaluate & Select
   └── Inspect returned summaries (zero LLM token waste)
   └── Identify top 2-5 URLs directly relevant to the query

Phase 3: Deep Extraction
   └── web_crawl_get_page (for each selected URL)
       └── Read full cached markdown directly from SQLite cache

Phase 4: Synthesis
   └── Produce final concise summary/report for the user

Best Practices

  1. Never use contentDepth: "full" on large crawls. It returns full markdown for every discovered page in one response, which can overflow context windows. Use summary first.
  2. Use includePatterns / excludePatterns.
    • Include: ["/docs/*", "/api/*", "/guide/*"]
    • Exclude: ["/changelog/*", "/blog/*", "/privacy*"]
  3. Fallback to web_scrape. If web_crawl discovers external links outside sameHostOnly, call web_scrape individually on those key external links.
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. 10d ago First seen · 40 lines · 72 tokens per session scan A 328d8e67ea1c

Subscribe to this mod's changes

web-researcher is a skill published in the GitHub repository creatorpiyush/webmesh-mcp (0 stars, last pushed 25d ago), licensed MIT. It adds 72 tokens to every session and 406 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens