A web-browsing skill for fetching pages, extracting content, crawling sites, and automating browser interactions. It uses ordinary web requests first and a browser when JavaScript is needed.

Scraping pages, extracting structured fields, checking claims, monitoring site changes, and performing browser actions.

It gives a coding assistant a defined way to work with websites instead of relying only on text supplied in the chat.

web-agent — Skill for Claude Code and Codex by creatorpiyush

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-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-agent/github.svg)](https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-agent)

Your own site

<a href="https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-agent"><img src="https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/creatorpiyush/webmesh-mcp/web-agent"><img src="https://agentmods.dev/badge/skills/creatorpiyush/webmesh-mcp/web-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,287 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.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.02287
Opus 5.5	$0.00045	$0.00915
Sonnet 5.5	$0.00023	$0.00457
Haiku 4.5	$0.00011	$0.00229

Measured 2mo ago against content hash 177dc7bc56e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

web-agent 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 2mo 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-agent/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Agent Skill

This skill gives you access to the webmesh-mcp MCP server — a token-economical web browsing, scraping, and crawling suite. All tools respect robots.txt by default.

MCP Server Setup

The server can be registered in your MCP config via npm:

{
  "mcpServers": {
    "web-agent": {
      "command": "npx",
      "args": ["webmesh-mcp"]
    }
  }
}

Or from source:

{
  "mcpServers": {
    "web-agent": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/webmesh-mcp/src/index.ts"]
    }
  }
}

Tool Reference

`web_scrape`

Fetches a URL and returns clean content. Tries static HTTP first; escalates to Playwright Chromium only if the page requires JavaScript to render.

Parameters:

Name	Type	Default	Description
`url`	string (URL)	—	Page to scrape
`format`	`"markdown"` or `"json"`	`"markdown"`	Output format
`schema`	`Record<string, string>`	—	`{field: cssSelector}` — required when `format="json"`
`selector`	string	—	Scope markdown extraction to this CSS subtree
`forceBrowser`	boolean	false	Skip static fetch, always use Chromium
`ignoreRobots`	boolean	false	Bypass robots.txt disallow rules

Use when: You want the readable content of a page, or need to extract specific fields.

Example (markdown):

{ "url": "https://example.com", "format": "markdown" }

Example (schema JSON):

{
  "url": "https://pypi.org/project/requests/",
  "format": "json",
  "schema": { "name": "h1.package-header__name", "version": ".release__version" }
}

`web_check`

Verifies a claim about a page without returning full content. Returns pass: true/false and a short evidence snippet (200 chars max).

Parameters:

Name	Type	Default	Description
`url`	string (URL)	—	Page to check
`assertion`	enum	—	`contains`, `not_contains`, `selector_exists`, `selector_not_exists`, `text_equals`
`value`	string	—	Text to find, or CSS selector for selector_* assertions
`selector`	string	—	Scope text search to this CSS subtree
`forceBrowser`	boolean	false	Use Chromium
`ignoreRobots`	boolean	false	Bypass robots.txt

Read the full file on GitHub · 274 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.

2mo ago First seen · 274 lines · 113 tokens per session scan A 177dc7bc56e6

Subscribe to this mod's changes

web-agent is a skill published in the GitHub repository creatorpiyush/webmesh-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 2,287 once invoked, about $0.0005 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 2026-08-31.

Browser automation Research

web-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
web-agentcreatorpiyush/webmesh-mcp	Skill	0	2mo ago	MIT	A	113	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	today	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	today	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	yesterday	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.9k	today	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	906	yesterday	MIT	A	40	Claude Code