A command for visiting and reading a web page when someone provides its URL. It is intended for checking reference sites, documentation, competitor pages, and service-status pages directly.

Use it to fetch a supplied website or documentation URL and extract its layout, features, navigation, API details, examples, or current status.

It avoids guessing what a linked page contains. The page can be inspected before making plans, implementing an integration, or explaining its contents.

How ccivlcid/VibeHarness configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ccivlcid/VibeHarness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ccivlcid/VibeHarness/main/.claude/commands/web-fetch.md

Clone the repo

git clone --depth 1 https://github.com/ccivlcid/VibeHarness

Made for: Claude Code.

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/commands/ccivlcid/vibeharness/web-fetch.svg)](https://agentmods.dev/commands/ccivlcid/vibeharness/web-fetch)

Your own site

<a href="https://agentmods.dev/commands/ccivlcid/vibeharness/web-fetch"><img src="https://agentmods.dev/badge/commands/ccivlcid/vibeharness/web-fetch.svg" alt="Measured on agentmods" 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 577 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	$0.00000	$0.00577
Opus 5	$0.00000	$0.00289
Sonnet 5	$0.00000	$0.00115
Haiku 4.5	$0.00000	$0.00058

Measured 6d ago against content hash 8db28c63bc5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-fetch 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 6d 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.

.claude/commands/web-fetch.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Fetch — Visit URLs Directly

This command is part of the VibeHarness framework.

Core principle: When a URL is given, visit it directly. Don't guess what's on the page.

Non-developers often share reference sites, competitor pages, or documentation links. This skill lets you fetch and analyze those pages directly.

When to Fetch

During Planning

Non-developer shares a reference site ("make it like this")
Competitor or similar service analysis
Checking a specific API documentation page

During Development

Reading API docs at a specific URL
Checking a library's official page for usage examples
Verifying deployment or service status pages

During Communication

Non-developer asks "what does this site do?"
Summarizing a page's content for planning discussions

How to Fetch

Use the WebFetch MCP tool:

Extract the URL from the non-developer's message
Call WebFetch with the URL
Analyze the returned content
Present findings appropriate to the context

What to Extract

Scenario	Focus On
Reference site ("like this")	Layout, features, navigation, visual style, UX patterns
API documentation	Endpoints, auth, request/response format, rate limits
Content page	Key information, summaries, actionable items
Competitor analysis	Feature set, pricing model, user flow

Presenting Results

For planning docs (docs/biz/):

"The reference site has these main features: ..."
"Their user flow goes: landing → signup → dashboard → ..."
"Key design patterns: sidebar navigation, card-based layout"

For technical docs (docs/ai-dev/):

API endpoint details, auth methods
Technology stack observations (if detectable)

For non-developers (direct response):

Simple language, no technical jargon
Focus on what the site does, not how it's built
"This site lets users do X, Y, Z. The main screen shows..."

Limitations

Login-required pages: Can't access content behind authentication
JavaScript-heavy SPAs: May get only initial HTML, not dynamic content
Blocked access: Some sites block automated requests

Read the full file on GitHub · 76 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.

6d ago First seen · 76 lines · 0 tokens per session scan A 8db28c63bc5e

Subscribe to this mod's changes

web-fetch is a command published in the GitHub repository ccivlcid/VibeHarness (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 577 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 2026-08-31.

Browser automation Research

VibeHarness: Command for Claude Code