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 MSApps-Mobile/claude-plugins --skill chrome-health-checkgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/chrome-health-check)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/chrome-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/chrome-health-check/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/msapps-mobile/claude-plugins/chrome-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/chrome-health-check.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 | $0.00085 | $0.01841 |
| Opus 5 | $0.00043 | $0.00920 |
| Sonnet 5 | $0.00017 | $0.00368 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
chrome-health-check 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Connection Health Check
Run a quick connection test. If broken, diagnose the root cause and fix it.
Step 1: Test the connection
Call tabs_context_mcp with createIfEmpty: false.
If successful (returns tab info or "no tab group exists"): → Report: "✅ Chrome is connected and ready." Stop here.
If it returns "No Chrome extension connected after discovery": → Report: "❌ Chrome extension not connected — diagnosing now…" → Before assuming Chrome is closed, run Step 1b to distinguish "Chrome closed" from "extension not paired". → Then proceed to Step 2.
Step 1b: Distinguish closed vs. unpaired Chrome
Even when tabs_context_mcp fails, Chrome may be running — the extension just isn't paired to this session. Run these two checks before escalating.
Check A: Control_Chrome tab list
Call mcp__Control_Chrome__list_tabs (no args needed).
- Returns a list of tabs → Chrome IS running. The extension is simply not paired to this session. Tell the user: "Chrome is open but the Claude extension isn't connected — please click the Claude extension icon in your Chrome toolbar and hit Connect." Stop here unless they need more help.
- Returns error or empty → Chrome may actually be closed → proceed to Step 2.
⚠️ Important (observed 2026-05-03):
Control_Chrome.list_tabsandopen_urlsucceed even with no Claude-in-Chrome connection. However,get_page_contentandexecute_javascriptwill still fail with "Google Chrome is not running." This is a known limitation of Control_Chrome's DOM layer — it does NOT mean Chrome is closed. Trustlist_tabsfor the liveness check.
Check B: Computer-use screenshot (visual backup)
If computer-use is available, call mcp__computer-use__request_access for Google Chrome, then take a screenshot. Chrome will be granted as read-tier (visible but not clickable). A screenshot showing the Chrome window with tabs confirms Chrome is running regardless of tool errors.
Chrome is always read-only via computer-use (tier "read") — you can see the screen but cannot click or type. For actual browser interaction, the Claude-in-Chrome extension must be connected.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 163 lines · 85 tokens per session scan A 703e2e14f722
chrome-health-check is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 14d ago), licensed MIT. It adds 85 tokens to every session and 1,841 once invoked, about $0.0004 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.
Other skills, from other repositories
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).
web-fetch
Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.
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…
legal-iros-registry-automation
A guide for helping automate bulk requests for company or property registry certificates from South Korea’s Supreme Court Internet Registry Office (IROS). The user handles login, authentication, and payment in the browser, while the workflow assists with collecting, saving, and reporting the documents.
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
vibe-behavioral-test-capture
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture generation.