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 skills add yunsii/wezdeck --skill chrome-devtoolsgit clone --depth 1 https://github.com/yunsii/wezdeckWrote 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/skills/yunsii/wezdeck/chrome-devtools)<a href="https://agentmods.dev/skills/yunsii/wezdeck/chrome-devtools"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/chrome-devtools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yunsii/wezdeck/chrome-devtools"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/chrome-devtools.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01292 |
| Opus 5.5 | $0.00018 | $0.00517 |
| Sonnet 5.5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
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 1mo 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) | 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.json → mcp.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 dozens of tools (count drifts by release)
openclaw mcp reload
# or: systemctl --user restart openclaw-gateway.service
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.
- 1mo ago Changed 157bd8958bad
- 1mo ago Changed 3d9808c380d5
- 1mo ago First seen · 116 lines · 44 tokens per session scan A 92efa978599a
chrome-devtools is a skill published in the GitHub repository yunsii/wezdeck (4 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 1,292 once invoked, about $0.0002 per session on Opus 5.5. 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.
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…
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
computer-use
Desktop control that picks the right interface per step — app scripting (AppleScript/JXA), accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.
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…