web-developer-mcp CLAUDE.md

A set of project instructions for a web-development MCP server, a connector that lets an AI use browser tools through Playwright.

In plain words
What is it for?
It supports building and maintaining browser tools such as navigation, clicking, form filling, page inspection, HTML extraction, and form submission.
Why use it?
It gives the coding agent shared rules for code style, project organization, and browser handling, reducing inconsistent changes.

Instructions file

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.

agentmods
npx agentmods add instructions/artmann/web-developer-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Artmann/web-developer-mcp
Per session 1,161 This file is loaded in full into every session.
When invoked 1,161 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01161 $0.01161
Opus 5 $0.00580 $0.00580
Sonnet 5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 2d ago against content hash 01a21d06f8ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-developer-mcp CLAUDE.md 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 2d 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.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Instructions for WebDev MCP Server

This is a Model Context Protocol (MCP) server for web development that provides browser automation tools using Playwright.

Development Guidelines

Code Style & Organization

  • Use TypeScript with strict type checking
  • Follow alphabetical sorting for object properties and interface fields
  • Use early returns to reduce nesting
  • Add blank lines between methods and logical sections
  • Prefer as const for literal types to ensure proper MCP content typing
  • Use globalThis as any for browser globals in Playwright evaluation contexts

Project Structure

src/
├── index.ts                    # Entry point with error handling
├── server.ts                   # MCP server setup and tool registration
├── browser/
│   └── BrowserManager.ts      # Singleton browser management
└── tools/
    ├── click.ts               # Element clicking
    ├── console.ts             # Console output retrieval
    ├── fill.ts                # Form input filling
    ├── navigate.ts            # Browser navigation
    ├── query-dom.ts           # DOM element inspection
    ├── query-html.ts          # HTML extraction
    └── submit.ts              # Form submission

Browser Management

  • Uses singleton pattern for consistent browser state
  • Single browser instance with single page (replaces page on navigation)
  • Captures console logs automatically on page load
  • Supports graceful shutdown via signal handlers
  • Navigation State Management: Uses isNavigating state to coordinate timing between tools
  • Automatic Waiting: Tools wait for navigation completion before executing to ensure dynamic content is captured

Tool Development

  • Each tool is a separate module exporting a handler function
  • All handlers must return MCP-compatible content with type: 'text' as const
  • Include proper error handling with descriptive messages
  • Add parameter validation and helpful error messages for missing page state
  • Navigation-Dependent Tools: Console, DOM query, and HTML extraction tools must call waitForNavigationComplete() before execution
  • Timing Considerations: Allow additional time (1s) after navigation for JavaScript execution and dynamic content creation

Read the full file on GitHub · 147 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.

  1. 2d ago First seen · 147 lines · 1,161 tokens per session scan A 01a21d06f8ff

Subscribe to this mod's changes

web-developer-mcp CLAUDE.md is an instructions file published in the GitHub repository Artmann/web-developer-mcp (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,161 tokens to every session, about $0.0058 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.