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 Enablement-Engineering/gobbler --skill gobbler-browsergit clone --depth 1 https://github.com/Enablement-Engineering/gobblerWrote 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/enablement-engineering/gobbler/gobbler-browser)<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>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 | $0.00054 | $0.02644 |
| Opus 5 | $0.00027 | $0.01322 |
| Sonnet 5 | $0.00011 | $0.00529 |
| Haiku 4.5 | $0.00005 | $0.00264 |
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.
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 statusdoes 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
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.
- 7d ago First seen · 412 lines · 54 tokens per session scan A f737ed5e1894
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.
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).
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…
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…
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.
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.
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…