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 agentmods add skills/evalvis/webreadmcp/skillnpx skills add EvalVis/webreadmcp --skill skillgit clone --depth 1 https://github.com/EvalVis/webreadmcpWhat 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 | $0.00044 | $0.00520 |
| Opus 5 | $0.00022 | $0.00260 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
webread scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Search the web and extract content from webpages using curl and bash/bat. Use when the user wants to search the web, look something up online, read a webpage, or extract information from a URL. What it actually says
Web Read
Web Search
Use the appropriate script for the OS. Pass the query and an optional search page number (most of the time there are lots of results and they are split to multiple pages. Page number defaults to 1).
Linux / macOS / Git Bash:
bash skill/scripts/linux/web_search.sh "your search query" [page]
Windows:
skill\scripts\windows\web_search.bat "your search query" [page]
Examples:
bash skill/scripts/linux/web_search.sh "rust async tutorial"
skill\scripts\windows\web_search.bat "python web frameworks" 2
Returns numbered titles with links.
Reading a Webpage
Non-raw HTML
Linux / macOS / Git Bash:
curl -s -L -A "Mozilla/5.0" "https://example.com" | sed 's/<script[^>]*>.*<\/script>//g; s/<style[^>]*>.*<\/style>//g; s/<[^>]*>//g; /^$/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.
- yesterday 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 6mo ago), licensed MIT. It adds 44 tokens to every session and 520 once invoked, about $0.0002 per session on Opus 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
gpt-researcher
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API…
gpt-researcher
Autonomous deep research from Codex via MCP.
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.
vexor-cli
Semantic file discovery via vexor. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing.
agent-web-search
Search the live web through the agent-web-search CLI when current sources, online research, or cross-provider web results are needed and the agent is using shell tools instead of MCP.
searxng-web-search
Privacy-respecting web metasearch via the searxng-mcp MCP server. Use when the agent needs current, open-web results for a query and must NOT leak the query to a single tracking engine — SearXNG aggregates many engines (Google, Bing, DuckDuckGo, Wikipedia, …) behind one JSON tool. Use for general lookups…