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 skills/ggprompts/tabzchrome/browsernpx skills add GGPrompts/TabzChrome --skill browsergit clone --depth 1 https://github.com/GGPrompts/TabzChromeWrote 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/ggprompts/tabzchrome/browser)<a href="https://agentmods.dev/skills/ggprompts/tabzchrome/browser"><img src="https://agentmods.dev/badge/skills/ggprompts/tabzchrome/browser.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 | $0.00036 | $0.00887 |
| Opus 5 | $0.00018 | $0.00443 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
browser 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 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.
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.
This is a copy
88% identical to tabz-browser — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TabzChrome Browser Automation
Control Chrome via MCP tools for screenshots, interaction, debugging, and notifications.
Quick Start
Use mcp-cli to discover and call tools:
# Get tool schema (REQUIRED before calling)
mcp-cli info tabz/tabz_screenshot
# Call tool
mcp-cli call tabz/tabz_screenshot '{}'
Core Workflows
Screenshot a Page
# Get current tab info
mcp-cli call tabz/tabz_get_page_info '{}'
# Take screenshot
mcp-cli call tabz/tabz_screenshot '{}'
# Returns file path - use Read tool to view
Debug Network/API Issues
# 1. Enable capture BEFORE triggering action
mcp-cli call tabz/tabz_enable_network_capture '{}'
# 2. Trigger the action on page
# 3. Get failed requests (status >= 400)
mcp-cli call tabz/tabz_get_network_requests '{"statusMin": 400}'
# 4. Check console for JS errors
mcp-cli call tabz/tabz_get_console_logs '{"level": "error"}'
Test Responsive Design
# Emulate device
mcp-cli call tabz/tabz_emulate_device '{"device": "iPhone 14"}'
# Take screenshot
mcp-cli call tabz/tabz_screenshot '{}'
# Clear emulation
mcp-cli call tabz/tabz_emulate_clear '{}'
Fill and Submit Form
mcp-cli call tabz/tabz_fill '{"selector": "#email", "value": "[email protected]"}'
mcp-cli call tabz/tabz_click '{"selector": "button[type=submit]"}'
Notify User (TTS)
mcp-cli call tabz/tabz_speak '{"text": "Task complete"}'
Performance Profiling
mcp-cli call tabz/tabz_profile_performance '{}'
# Returns: DOM nodes, JS heap, event listeners, timing
DOM Tree Inspection
mcp-cli call tabz/tabz_get_dom_tree '{"maxDepth": 3}'
Tool Categories
| Category | Count | Key Tools |
|---|---|---|
| Screenshots | 2 | screenshot, screenshot_full |
| Interaction | 4 | click, fill, get_element |
| Network | 3 | enable_network_capture, get_network_requests |
| DOM/Debug | 4 | get_dom_tree, get_console_logs, profile_performance |
| Emulation | 6 | emulate_device, emulate_geolocation |
| Audio/TTS | 3 | speak, list_voices, play_audio |
| Tabs | 5 | list_tabs, open_url, switch_tab |
| Cookies | 5 | cookies_get, cookies_list |
What ships with it
10 files 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.
- references/advanced-tools.md 15 KB
- references/browser-data.md 12 KB
- references/core-tools.md 18 KB
- references/form-automation.md 1.4 KB
- references/network-debugging.md 1.5 KB
- references/network-downloads.md 6.6 KB
- references/profiles-and-plugins.md 8.5 KB
- references/screenshot-workflows.md 971 B
- references/tts-notifications.md 954 B
- references/windows-groups.md 12 KB
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 · 126 lines · 36 tokens per session scan A a80d43d4b519
browser is a skill published in the GitHub repository GGPrompts/TabzChrome (146 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 887 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to tabz-browser, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…