gobbler-browser

gobbler-browser is a skill for Claude Code from Enablement-Engineering/gobbler. It costs 54 tokens per session (2,644 once invoked), scanned A, original, MIT.

A browser-control add-on that lets an agent navigate tabs, run JavaScript, and extract page content through the Gobbler extension. It also connects to NotebookLM, Claude, ChatGPT, and Gemini in the browser.

In plain words
What is it for?
Use it to list and control selected browser tabs, extract a page as Markdown, inject page controls, or work with supported AI chat websites.
Why use it?
It removes the need to copy information manually between web pages and the agent. Browser-based AI integrations may stop working when those sites change their page layout.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Part of the gobbler plugin — 3 skills, 1 command, 1 MCP server shipped together

Good fit Use it to list and control selected browser tabs, extract a page as Markdown, inject page controls, or work with supported AI chat websites.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/enablement-engineering/gobbler/gobbler-browser
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.

Any agent
npx skills add Enablement-Engineering/gobbler --skill gobbler-browser
Clone the repo
git clone --depth 1 https://github.com/Enablement-Engineering/gobbler

Made for: Claude Code.

Or install gobbler, the plugin that ships this one along with the rest of its 3 skills, 1 command, 1 MCP server.

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 gobbler-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/enablement-engineering/gobbler/gobbler-browser.svg)](https://agentmods.dev/skills/enablement-engineering/gobbler/gobbler-browser)
Your own site
<a href="https://agentmods.dev/skills/enablement-engineering/gobbler/gobbler-browser"><img src="https://agentmods.dev/badge/skills/enablement-engineering/gobbler/gobbler-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00054 $0.02644
Opus 5 $0.00027 $0.01322
Sonnet 5 $0.00011 $0.00529
Haiku 4.5 $0.00005 $0.00264

Measured 7d ago against content hash f737ed5e1894, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gobbler-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 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.

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.

skills/gobbler-browser/SKILL.md · 412 lines

How it starts

The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gobbler Browser

Control the browser via the Gobbler CLI and browser extension. Includes integrations for AI chat services.

Requires:

  • Gobbler browser extension installed
  • Target tabs in the specific extension-managed group ID
  • Local relay; most browser operations auto-start it, but browser status does not

Note: AI chat integrations (NotebookLM, Claude, ChatGPT, Gemini) use DOM automation and may break when sites update their UI.


Quick Start

# Check browser connection
gobbler relay start
gobbler browser status

# List tabs in Gobbler group
gobbler browser list

# Re-inject page APIs if automatic injection did not occur
gobbler browser inject

# Extract current page to markdown
gobbler browser extract -o page.md

Core Browser Commands

Check Status

gobbler browser status

Shows relay status and number of connected extensions.

List Tabs

# All tabs in Gobbler group
gobbler browser list

# Filter by site
gobbler browser list --filter notebooklm
gobbler browser list --filter claude
gobbler browser list --filter chatgpt
gobbler browser list --filter gemini

# JSON output
gobbler browser list --json

Inject APIs

Inject page-specific APIs into matching tabs in the Gobbler group. The extension normally injects on matching grouped tabs and navigation; use this command after browser/extension reload or when automatic injection did not occur.

gobbler browser inject

Open URLs

# Open one or more URLs in Gobbler tab group
gobbler browser open "https://example.com"
gobbler browser open "https://example.com" "https://google.com"

# Read URLs from file
gobbler browser open -f urls.txt

Navigate Current Tab

gobbler browser navigate "https://example.com"

Extract Page Content

# Full page as markdown
gobbler browser extract

# Save to file
gobbler browser extract -o page.md

# With CSS selector
gobbler browser extract --selector "article.content"

# From specific tab
gobbler browser extract --tab 1234567890

Read the full file on GitHub · 412 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 · 412 lines · 54 tokens per session scan A f737ed5e1894

Subscribe to this mod's changes

gobbler-browser is a skill published in the GitHub repository Enablement-Engineering/gobbler (4 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 2,644 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

computer-use

OS/window-level inspection and input in visible local app windows through orca computer: native apps, external browser windows (Chrome, Edge, Safari), and app webviews. Not for Orca's embedded browser (use orca-cli) or page-only automation (use Playwright or CDP).

stablyai/orca · 62 tokens

opencli-browser

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…

jackwener/OpenCLI · 80 tokens

opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…

jackwener/OpenCLI · 88 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens

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.

jackwener/OpenCLI · 67 tokens

opencli-browser-sitemap

Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…

jackwener/OpenCLI · 64 tokens