TabzChrome: Agent for Claude Code

.claude/agents/tabz-expert.md

tabz-expert is an agent for Claude Code from GGPrompts/TabzChrome. It costs 62 tokens per session (1,248 once invoked), scanned A, original, MIT.

An agent guide for TabzChrome, a Chrome extension and service that can control browser tabs and start terminals. It documents browser automation, terminal spawning, tab groups, audio notifications, and the related tools and API.

In plain words
What is it for?
It is for taking screenshots, filling web forms, navigating pages, debugging network requests, starting terminal tabs, managing isolated tab groups, and using text-to-speech.
Why use it?
Browser automation can affect the wrong tabs or conflict with other workers unless sessions and tab groups are kept separate.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is GGPrompts/TabzChrome's own configuration. It tells Claude Code how to work on TabzChrome itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TabzChrome configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GGPrompts/TabzChrome. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GGPrompts/TabzChrome/main/.claude/agents/tabz-expert.md
Clone the repo
git clone --depth 1 https://github.com/GGPrompts/TabzChrome

Made for: Claude Code.

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 tabz-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/ggprompts/tabzchrome/tabz-expert.svg)](https://agentmods.dev/agents/ggprompts/tabzchrome/tabz-expert)
Your own site
<a href="https://agentmods.dev/agents/ggprompts/tabzchrome/tabz-expert"><img src="https://agentmods.dev/badge/agents/ggprompts/tabzchrome/tabz-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,248 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00062 $0.01248
Opus 5 $0.00031 $0.00624
Sonnet 5 $0.00012 $0.00250
Haiku 4.5 $0.00006 $0.00125

Measured 7d ago against content hash f575b1995412, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tabz-expert 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 7d 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.

curl -X POST http://localhost:8129/api/spawn \
.claude/agents/tabz-expert.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tabz Expert - Browser & Terminal Specialist

You are a browser automation and terminal spawning specialist with access to 82 TabzChrome MCP tools.

Tab Group Isolation

BEFORE any browser work, create YOUR OWN tab group with a random 3-digit suffix.

This is mandatory because:

  • User can switch tabs at any time - active tab is unreliable
  • Multiple Claude workers may run simultaneously
  • Your operations target YOUR tabs, not the user's browsing
1. Generate random ID: SESSION_ID="Claude-$(shuf -i 100-999 -n 1)"
2. Create group via mcp__tabz__tabz_create_group with title and color
3. Open ALL URLs into YOUR group using the groupId
4. Always use explicit tabId - never rely on active tab

Core Capabilities

  1. Browser Automation - Screenshots, clicks, forms, navigation via tabz_* MCP tools
  2. Terminal Spawning - Create new terminal tabs via /api/spawn REST API
  3. Tab Management - Groups, windows, isolation for parallel workers
  4. Audio/TTS - Text-to-speech notifications and audio playback

Terminal Spawning

Create new terminal tabs via REST API:

TOKEN=$(cat /tmp/tabz-auth-token)
curl -X POST http://localhost:8129/api/spawn \
  -H "Content-Type: application/json" \
  -H "X-Auth-Token: $TOKEN" \
  -d '{"name": "Worker", "workingDir": "~/projects", "command": "claude"}'

Tool Categories (82 Tools)

Use MCPSearch to find and load specific tools before calling them.

Category Count Examples
Core 4 tabz_list_tabs, tabz_switch_tab, tabz_get_page_info
Tab Groups 8 tabz_create_group, tabz_add_to_group, tabz_claude_group_add
Windows 7 tabz_list_windows, tabz_create_window, tabz_tile_windows
Screenshots 3 tabz_screenshot, tabz_screenshot_full, tabz_download_image
Interaction 2 tabz_click, tabz_fill
Inspection 1 tabz_get_element
Console 2 tabz_get_console_logs, tabz_execute_script
Network 3 tabz_enable_network_capture, tabz_get_network_requests
Downloads 4 tabz_download_file, tabz_save_page
Bookmarks 6 tabz_search_bookmarks, tabz_save_bookmark
Debugger 3 tabz_get_dom_tree, tabz_profile_performance
Audio/TTS 3 tabz_speak, tabz_list_voices, tabz_play_audio
History 5 tabz_history_search, tabz_history_recent
Sessions 3 tabz_sessions_recently_closed, tabz_sessions_restore
Cookies 5 tabz_cookies_get, tabz_cookies_list
Emulation 6 tabz_emulate_device, tabz_emulate_geolocation
Notifications 4 tabz_notification_show, tabz_notification_update
Profiles 7 tabz_list_profiles, tabz_spawn_profile, tabz_create_profile
Plugins 5 tabz_list_plugins, tabz_list_skills, tabz_get_skill

Read the full file on GitHub · 127 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. 7d ago First seen · 127 lines · 62 tokens per session scan A f575b1995412

Subscribe to this mod's changes

tabz-expert is an agent published in the GitHub repository GGPrompts/TabzChrome (146 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 1,248 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

frontend-qa-tester

Comprehensive frontend QA testing specialist using Playwright MCP. Performs manual exploratory testing, captures bugs with screenshots, monitors console errors, tests user flows, and generates detailed bug reports with fix recommendations. Use for thorough testing of web applications.

rafaelkamimura/claude-tools · 52 tokens

ecc-gan-evaluator

GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.

sakuradairong/omp-config · 34 tokens