chrome-devtools

A skill for controlling a Chrome browser that is running with remote debugging enabled. It supports navigation, page snapshots, screenshots, clicks, form entry, and inspection of browser console and network activity.

In plain words
What is it for?
Opening URLs, checking changed interfaces, clicking buttons, completing forms, taking screenshots, and investigating browser console or network problems.
Why use it?
It lets an agent inspect and operate the actual browser page instead of relying only on downloaded HTML. This helps reveal broken interactions, visible errors, and failed network requests.

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

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00044 $0.01273
Opus 5 $0.00022 $0.00636
Sonnet 5 $0.00009 $0.00255
Haiku 4.5 $0.00004 $0.00127

Measured 2d ago against content hash 92efa978599a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chrome-devtools 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| User: open/check URL, click, form, screenshot | MCP navigate + snapshot (not curl HTML) |
openclaw/workspace/skills/chrome-devtools/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chrome DevTools (Dex / OpenClaw core)

What this is

Dex (Main) can control the Windows host debug Chrome through OpenClaw MCP:

Piece Where
CDP endpoint http://127.0.0.1:9222 (WezDeck helper auto-start)
MCP server name chrome-devtools in local ~/.openclaw/openclaw.jsonmcp.servers
Package globally-installed chrome-devtools-mcp --browser-url=http://127.0.0.1:9222 --usageStatistics=false (pinned; not npx …@latest)

This is not the same MCP session as Grok/Claude CLI; all clients share the same Chrome process on port 9222. Avoid concurrent multi-agent browser wars.

Workflow detail for launch / badge / inspect: repo root docs/browser-debug.md.

When to use (Dex · Main)

Trigger Action
User: open/check URL, click, form, screenshot MCP navigate + snapshot (not curl HTML)
You just changed UI (allowlisted repo) Before 验收通过: open relevant URL/path, snapshot
“页面坏了 / 控制台报错 / 按钮点不了” list pages / console / network as needed

Coding agents on the host have their own browser/MCP/profile — this skill is for main when main is looking at the page. No bridge required.

When not to use

  • Pure git / shell / ledger / worktree assess — do not open Chrome “just in case”.
  • Destructive browser actions outside what the user asked (clear profile, mass delete, payment submit) without explicit confirmation.
  • Host shell risk still goes through claw-run / exec-risk — browser MCP is separate.

Operator setup (once per machine)

# CDP must answer first
curl -sS -m 3 http://127.0.0.1:9222/json/version

# Install once, pinned. Never drive this from `npx …@latest`: npx leaves
# npm-cli resident (~85Mi) per instance purely as a launcher.
npm i -g [email protected]

openclaw mcp add chrome-devtools \
  --command chrome-devtools-mcp \
  --arg --browser-url=http://127.0.0.1:9222 \
  --arg --usageStatistics=false \
  --timeout 90 \
  --connect-timeout 60

openclaw mcp probe chrome-devtools   # expect ~29 tools
openclaw mcp reload
# or: systemctl --user restart openclaw-gateway.service

Read the full file on GitHub · 116 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 · 116 lines · 44 tokens per session scan A 92efa978599a

Subscribe to this mod's changes

chrome-devtools is a skill published in the GitHub repository yunsii/wezdeck (5 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 1,273 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.

Related

Other skills, from other repositories

launch

Launch and automate VS Code (Code OSS) using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test UI features, or take screenshots of VS Code. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch…

workstream-labs/workstreams · 80 tokens

webapp-testing

Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.

Hmbown/CodeWhale · 32 tokens

tutti-workspace-app-factory

Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…

tutti-os/tutti · 138 tokens

tutti-record-agent-session-replay

From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay…

tutti-os/tutti · 127 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

browser

Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron desktop apps — navigating, filling forms, clicking, screenshots, extracting data, testing web apps, visual UI checks, the Pi Dashboard's Electron shell, or the user's own logged-in browser (SSO/2FA sites). Triggers…

BlackBeltTechnology/pi-agent-dashboard · 92 tokens