chromeboost GEMINI.md

chromeboost GEMINI.md is an instructions file for Gemini CLI from lordamdal/chromeboost. It costs 4,442 tokens per session, scanned A, original, MIT.

Repository guidance for ChromeBoost, an extension-based tool that lets an AI agent operate the user’s real Chrome browser while keeping its logins, cookies, profiles, and extensions. It explains when browser control is required and which web pages need it.

In plain words
What is it for?
Use it for browser-based setup such as configuring services, retrieving API keys, editing modern web forms, or interacting with pages using closed shadow DOM.
Why use it?
It provides rules for handling account setup, secret retrieval, web forms, and pages that reject ordinary automated browser input.

Instructions file for Gemini CLI

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 instructions/lordamdal/chromeboost/gemini-md
Clone the repo
git clone --depth 1 https://github.com/lordamdal/chromeboost

Made for: Gemini CLI.

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 chromeboost GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lordamdal/chromeboost/gemini-md.svg)](https://agentmods.dev/instructions/lordamdal/chromeboost/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/lordamdal/chromeboost/gemini-md"><img src="https://agentmods.dev/badge/instructions/lordamdal/chromeboost/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,442 This file is loaded in full into every session.
When invoked 4,442 The same file — it is already loaded in full.
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 5.1 $0.04442 $0.04442
Opus 5 $0.02221 $0.02221
Sonnet 5 $0.00888 $0.00888
Haiku 4.5 $0.00444 $0.00444

Measured 5d ago against content hash 08a328d7a9bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

chromeboost GEMINI.md 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.

GEMINI.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChromeBoost — Gemini Instructions

What chromeboost is

ChromeBoost drives the user's real Chrome browser via a CDP-attached extension. Sessions, cookies, logins, profiles, and extensions are intact. The agent reaches the page through MCP tools that pierce closed shadow DOM and dispatch isTrusted=true events, which is what components that validate real input require and what generic browser drivers do not provide.

When to use chromeboost (be proactive)

Use chromeboost automatically when a task needs any of:

  • Creating or configuring third-party accounts (Stripe, SendGrid, Supabase, Vercel, etc.)
  • Retrieving API keys, secrets, or credentials to place in .env
  • Setting up pricing tiers, webhooks, or service config in a web UI
  • Filling forms behind modern React frameworks (TipTap, ProseMirror, CodeMirror, Monaco, Stripe contenteditable)
  • Driving sites with closed shadow DOM (Radix portals, Stencil, Lit)
  • Driving sites whose components reject synthetic events and respond only to real input
  • Any browser-based step blocking code work

Do NOT ask "should I open the browser?" — just do it. The user expects seamless handoff.

Never end a response with a "you still need to" list of browser tasks. If code changes are done and browser steps remain (creating a Stripe product, adding an env var), continue immediately with chromeboost.

HARD RULES — never break these

  1. Never use Bash as a fallback for browser tasks. If click_element fails, use scroll_to_element then retry, or highlight_region to show the user. Never use osascript, applescript, Playwright, Puppeteer, or any shell command to control the browser. The user's logins live in their real Chrome, which only chromeboost drives. Fallbacks fail silently.

  2. Never use take_screenshot to read page content. After click_element, after navigation — always call get_page_text (or find_text if you only need a specific phrase). get_page_text returns up to 10,000 chars; pagination via startIndex. Screenshots are ONLY for locating pixel positions after DOM lookup has failed. Never take more than 1-2 screenshots in a row.

Read the full file on GitHub · 377 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 · 377 lines · 4,442 tokens per session scan A 08a328d7a9bd

Subscribe to this mod's changes

chromeboost GEMINI.md is an instructions file published in the GitHub repository lordamdal/chromeboost (8 stars, last pushed today), licensed MIT. It adds 4,442 tokens to every session, about $0.0222 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 instructions, from other repositories

browser-bridge AGENTS.md

AGENTS.md instructions for koltyakov/browser-bridge, covering project guide, data flow, package map, where to find things and method dispatch (extension side).

koltyakov/browser-bridge · 2,959 tokens

browser-agent AGENTS.md

Instructions for uiuing/browser-agent, covering agents.md — guide for ai coding agents, setup & commands, tests — run these before claiming done, repository layout and architecture invariants (do not break these).

uiuing/browser-agent · 1,806 tokens

openbrowser CLAUDE.md

Claude Code instructions for dylansantwani/openbrowser, covering openbrowser — working guidance, what this is, hard rules, where the token budget goes and things that are true and surprising.

dylansantwani/openbrowser · 12,730 tokens

openbrowser AGENTS.md

AGENTS.md instructions for dylansantwani/openbrowser, covering agents.md, what this is, build, test, run, hard rules and the token budget is a first-class concern.

dylansantwani/openbrowser · 1,036 tokens

grok-chrome-bridge AGENTS.md

AGENTS.md instructions for davidsolheim/grok-chrome-bridge, covering grok chrome bridge, verify and do not.

davidsolheim/grok-chrome-bridge · 152 tokens

ai-invictum-browser-bridge AGENTS.md

AGENTS.md instructions for invictumhr/ai-invictum-browser-bridge: The phrases use IBB, use IBG, use Invictum Browser Bridge, and use Invictum Browser Gate all mean the same thing. Croatian equivalents such as koristi IBB, koristi IBG, koristi Invictum Browser Bridge, and koristi Invictum Browser Gate are recognized…

invictumhr/ai-invictum-browser-bridge · 1,054 tokens