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 EvalVis/webreadmcp --skill skillgit clone --depth 1 https://github.com/EvalVis/webreadmcpWrote 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/evalvis/webreadmcp/skill)<a href="https://agentmods.dev/skills/evalvis/webreadmcp/skill"><img src="https://agentmods.dev/badge/skills/evalvis/webreadmcp/skill/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/evalvis/webreadmcp/skill"><img src="https://agentmods.dev/badge/skills/evalvis/webreadmcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.00520 |
| Opus 5.5 | $0.00018 | $0.00208 |
| Sonnet 5.5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
webread scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Search the web and extract content from webpages using curl and bash/bat. Use when the user wants to search the web, look something up online, read a webpage, or extract information from a URL. What it actually says
Web Read
Web Search
Use the appropriate script for the OS. Pass the query and an optional search page number (most of the time there are lots of results and they are split to multiple pages. Page number defaults to 1).
Linux / macOS / Git Bash:
bash skill/scripts/linux/web_search.sh "your search query" [page]
Windows:
skill\scripts\windows\web_search.bat "your search query" [page]
Examples:
bash skill/scripts/linux/web_search.sh "rust async tutorial"
skill\scripts\windows\web_search.bat "python web frameworks" 2
Returns numbered titles with links.
Reading a Webpage
Non-raw HTML
Linux / macOS / Git Bash:
curl -s -L -A "Mozilla/5.0" "https://example.com" | sed 's/<script[^>]*>.*<\/script>//g; s/<style[^>]*>.*<\/style>//g; s/<[^>]*>//g; /^$/d'
Windows:
Note: the below command can be executed on CMD if before the command you type: powershell -NoProfile -Command and envelop the command in parenthesis
(curl.exe -s -L -A "Mozilla/5.0" "https://example.com") -replace '<script[^>]*>.*?</script>','' -replace '<style[^>]*>.*?</style>','' -replace '<[^>]*>','' | Where-Object { $_.Trim() }
Raw HTML
Linux / macOS / Git Bash:
curl -s -L -A "Mozilla/5.0" "https://example.com"
Windows:
curl.exe -s -L -A "Mozilla/5.0" "https://example.com"
Requirements
curl(pre-installed on modern Windows, macOS, and Linux)- Linux/macOS:
bash
Installation
Copy the skill/ folder into your AI context folder.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 44 tokens per session scan A 9f9b01d3b754
webread is a skill published in the GitHub repository EvalVis/webreadmcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 520 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pixelbrowse
Screenshot and visually read any web page or document using pixelshot. Use instead of fetching raw HTML when you need to see what a page looks like, read visual content (charts, diagrams, infographics), check layouts, or verify UI. Triggers: "look at this page", "screenshot", "what does this site look like", "check…
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
ddgs
Use when an agent needs to search the web, find images/news/videos/books, or extract content from a URL. Covers the ddgs Python library, CLI, and MCP server integration.
tavily-hikari-crawl
Crawl bounded sites through Tavily Hikari with tvly-hikari.
algolia-crawler
Use this skill whenever a user wants to crawl one or more web pages or a whole site and turn them into an Algolia index using the Algolia CLI — especially for RAG, AI search, semantic search, or Agent Studio retrieval. Triggers: "index my website/docs with Algolia", "set up the Algolia Crawler", "crawl this page for…
browser-use
Automated browser control via the browser-use CLI. Navigate pages, fill forms, click elements, take screenshots, and extract content from the command line. Used by apply-to-job to drive real ATS portals end-to-end while the human watches.