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 instructions/antonzherdev/mcp-web-inspector/claude-mdgit clone --depth 1 https://github.com/antonzherdev/mcp-web-inspectorWrote 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/instructions/antonzherdev/mcp-web-inspector/claude-md)<a href="https://agentmods.dev/instructions/antonzherdev/mcp-web-inspector/claude-md"><img src="https://agentmods.dev/badge/instructions/antonzherdev/mcp-web-inspector/claude-md.svg" alt="Measured on agentmods" 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 | $0.03316 | $0.03316 |
| Opus 5 | $0.01658 | $0.01658 |
| Sonnet 5 | $0.00663 | $0.00663 |
| Haiku 4.5 | $0.00332 | $0.00332 |
Grade C, and why
mcp-web-inspector CLAUDE.md scanned grade C 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ./.mcp-web-inspector How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
This is a Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. It enables LLMs to interact with web pages, take screenshots, execute JavaScript, and perform HTTP requests through a set of MCP tools.
Server name: playwright-mcp (important for tool name length constraints - some clients like Cursor have a 60-character limit for server_name:tool_name)
Command Line Options
Session Persistence
By default, browser session data (cookies, localStorage, sessionStorage) is automatically saved and persists across browser restarts.
Available flags:
--no-save-session- Disable session persistence (start fresh each time)--user-data-dir <path>- Customize where session data is stored (default:./.mcp-web-inspector)--cdp-port <number>- Chromium remote-debugging port. Default: auto-pick the first free port starting at9222(so multiple parallel instances don't collide). Pass an explicit number to pin a port, or0to disable CDP entirely. When enabled, external Playwright clients can attach to the same browser viachromium.connectOverCDP("http://localhost:<port>")— useful for seed/login scripts that share cookies and the open page set with the MCP server. The resolved URL is surfaced via the MCPServerinstructionsfield at the initialize handshake. Security: the port has no authentication; anyone with local access to the machine can drive the browser. Disable on shared/multi-tenant hosts with--cdp-port 0.--warmup-browser- Launch Chromium at server startup instead of lazily on the first tool call. Off by default — sessions that never invoke an MCP tool shouldn't pay for Chromium startup. Combine with--cdp-portwhen external CDP clients (e.g. seed/login scripts) need the browser ready before any tool call has fired. Failures surface on the first real tool call rather than blocking startup.
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.
- 5d ago First seen · 327 lines · 3,316 tokens per session scan C f06ee687ac6b
mcp-web-inspector CLAUDE.md is an instructions file published in the GitHub repository antonzherdev/mcp-web-inspector (3 stars, last pushed 4mo ago), licensed MIT. It adds 3,316 tokens to every session, about $0.0166 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).