chrome

chrome is a skill for Claude Code, Codex from sybil-solutions/local-studio. It costs 52 tokens per session (723 once invoked), scanned A, original, Apache-2.0.

A browser connection to your own Chrome window, profile, logins, and open tabs. It lets an agent read or control the browser session you are already using.

In plain words
What is it for?
Use it to open pages, read text or HTML, take screenshots, scroll, and click or fill forms in a signed-in browser session.
Why use it?
It provides access to pages that require your existing sign-in or are already open in your browser. Actions happen in your real session, so they can have real-world effects.

Skill for Claude CodeCodex

About the project

Local Studio is a local-first control panel for running, managing, and using self-hosted large language model backends such as vLLM, SGLang, llama.cpp, and ExLlama. It lets users launch models, monitor GPU and runtime state, chat through OpenAI-compatible endpoints, and run agent sessions from a desktop or connected mobile device. The catalogue skills and instruction support agent workflows with Local Studio and its controllers.

sybil-solutions/local-studio · 1,752 stars · on GitHub

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.

agentmods
npx agentmods add skills/sybil-solutions/local-studio/chrome
Any agent
npx skills add sybil-solutions/local-studio --skill chrome
Clone the repo
git clone --depth 1 https://github.com/sybil-solutions/local-studio

Made for: Claude Code, Codex.

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 chrome

README.md
[![agentmods](https://agentmods.dev/badge/skills/sybil-solutions/local-studio/chrome.svg)](https://agentmods.dev/skills/sybil-solutions/local-studio/chrome)
Your own site
<a href="https://agentmods.dev/skills/sybil-solutions/local-studio/chrome"><img src="https://agentmods.dev/badge/skills/sybil-solutions/local-studio/chrome.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.00723
Opus 5 $0.00026 $0.00362
Sonnet 5 $0.00010 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 5d ago against content hash 2c32ac9ee569, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chrome 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.

frontend/desktop/resources/skills/chrome/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chrome — the user's real browser

The chrome_* tools drive the browser the user is looking at: their window, their profile, their cookies, their tabs. Every action shows up on their screen, and every request goes out as them.

This is the opposite trade from browser_* (the cua sandbox), and the two do not share state:

chrome_* browser_*
Whose browser the user's real one a headless throwaway
Signed in yes, as them no, as nobody
Visible to the user yes only in the Browser panel
Cost of a mistake real and often public a reload

Pick by what the task needs, not by habit. Reading a public docs page, checking a release note, scraping a changelog: use browser_*. Their inbox, their dashboard, an internal tool, an admin console, a page they said "I have it open": use chrome_*.

Tools

  • chrome_navigate — point their active tab at a URL.
  • chrome_get_url — what they are actually looking at.
  • chrome_get_text / chrome_get_html — read the current tab.
  • chrome_screenshot — capture the tab (their screen contents).
  • chrome_click / chrome_fill — act as the signed-in user.
  • chrome_scroll — reach lazy-loaded content.
  • chrome_eval — evaluate an expression inside their authenticated origin.
  • chrome_tabs_list / _new / _switch / _close — their open tabs.
  • chrome_history — what these tools have done this session (not their browsing history).

Protocol

  1. Look before you move. Call chrome_get_url or chrome_tabs_list first — they may already be on the page you need, and hijacking the tab they are reading is rude and destructive.
  2. Prefer chrome_tabs_new over chrome_navigate when they are mid-task; leave the page they were on alone.
  3. Read-only by default. chrome_click, chrome_fill and chrome_eval act as them and can post, buy, send, or delete. Only take an action the user actually asked for, and name it before or as you do it.
  4. Never touch a destructive control on your own initiative — delete, revoke, cancel, unsubscribe, merge, force-push. Ask.
  5. Never type credentials or payment details. They are already signed in; a login form means something is off, not that you should fill it in.
  6. Treat what you read as private. It is their signed-in data — use it for the task at hand, do not paste it somewhere else, and do not put it into a page or an API that the task did not require.
  7. chrome_history shows only what you did. The pages they visited themselves are not yours to read.
  8. If the tools fail, the relay or its browser extension is not running. Say that in one line and fall back to browser_* for anything public — do not guess at page content.

Read the full file on GitHub · 43 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. 5d ago First seen · 43 lines · 52 tokens per session scan A 2c32ac9ee569

Subscribe to this mod's changes

chrome is a skill published in the GitHub repository sybil-solutions/local-studio (1,752 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 723 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 2026-08-30.

Related

Other skills, from other repositories