chrome-devtools

chrome-devtools is a skill for Claude Code, Codex from fmind/dot. It costs 38 tokens per session (731 once invoked), scanned A, original, MIT.

A connection to a live Chrome browser for inspecting and automating web pages. It can examine performance, accessibility, cookies, network activity, and memory use.

In plain words
What is it for?
Use it to debug running websites, measure page performance, inspect browser state, check accessibility information, and investigate memory problems.
Why use it?
It helps find problems that are difficult to see from source code alone, such as slow rendering, inaccessible controls, broken requests, or memory leaks.

Skill for Claude CodeCodex

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 skills/fmind/dot/chrome-devtools
Any agent
npx skills add fmind/dot --skill chrome-devtools
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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.

agentmods badge for chrome-devtools

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/chrome-devtools.svg)](https://agentmods.dev/skills/fmind/dot/chrome-devtools)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/chrome-devtools"><img src="https://agentmods.dev/badge/skills/fmind/dot/chrome-devtools.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 731 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00038 $0.00731
Opus 5 $0.00019 $0.00365
Sonnet 5 $0.00008 $0.00146
Haiku 4.5 $0.00004 $0.00073

Measured yesterday against content hash 0c8d2dc9303d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

chrome-devtools 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 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.

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.

skills/chrome-devtools/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chrome DevTools

Chrome DevTools for agents connects AI coding agents to a live Chrome browser via the Model Context Protocol (MCP) or CLI. It enables automated browser inspection, performance tracing (Core Web Vitals, LCP), accessibility tree evaluation, cookie analysis, network inspection, and memory leak diagnosis. End-to-end browser journeys route through playwright; modern web standards and native patterns route through modern-web.

1. Configure MCP Server

Add the chrome-devtools MCP server to the current agent harness using agent-mcp:

# Project-scoped MCP registration (Antigravity CLI example)
agy mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest

2. Debugging and Auditing Workflow

  1. Launch browser session: Start Chrome with remote debugging enabled, or allow the MCP server to launch and control an isolated browser instance via Puppeteer.
  2. Performance and LCP: Record traces to identify slow rendering phases, server response latency, render-blocking resources, and Largest Contentful Paint culprits.
  3. Accessibility tree audits: Inspect computed accessible names, ARIA roles, and color contrast ratios to ensure WCAG compliance alongside quality-assurance.
  4. Memory and cookies: Take heap snapshots to identify detached DOM nodes and memory leaks; verify SameSite, Secure, and Partitioned cookie attributes.

Gotchas

  • Sensitive data exposure: The MCP server grants full inspection and execution control over the browser session; avoid using personal profiles or sharing sensitive credentials.
  • Headless versus headed: Automated testing runs headless by default; visual debugging and layout inspections may require headed mode.
  • Complementary to Playwright: Use Playwright for deterministic functional and E2E regression tests; reserve Chrome DevTools MCP for deep runtime profiling, traces, and live diagnostics.

Read the full file on GitHub · 51 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. yesterday First seen · 51 lines · 38 tokens per session scan A 0c8d2dc9303d

Subscribe to this mod's changes

chrome-devtools is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 731 once invoked, about $0.0002 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 2026-09-04.