What is fast-browser?

A command-line and agent workflow for controlling a persistent Chrome browser used in web automation. It keeps the browser open between tasks and uses page snapshots to interact with websites.

Fast browser navigation, clicking, typing, waiting, and other automated website interactions where bot detection may matter.

Keeping one browser session avoids repeated startup time and preserves cookies and other session data. Compact snapshots and batched actions also reduce the amount of work needed for multi-step tasks.

fast-browser — Skill for Claude Code and Codex by anusoft: A command-line and agent workflow for controlling a persistent…

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/anusoft/ultrastealth/fast-browser

Any agent

npx skills add anusoft/ultrastealth --skill fast-browser

Clone the repo

git clone --depth 1 https://github.com/anusoft/ultrastealth

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anusoft/ultrastealth/fast-browser.svg)](https://agentmods.dev/skills/anusoft/ultrastealth/fast-browser)

Your own site

<a href="https://agentmods.dev/skills/anusoft/ultrastealth/fast-browser"><img src="https://agentmods.dev/badge/skills/anusoft/ultrastealth/fast-browser.svg" alt="Measured on agentmods" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,110 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.

Model	Per session	Once invoked
Fable 5	$0.00096	$0.01110
Opus 5	$0.00048	$0.00555
Sonnet 5	$0.00019	$0.00222
Haiku 4.5	$0.00010	$0.00111

Measured 4d ago against content hash 5cf737e5f136, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fast-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 4d 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/fast-browser/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast Browser

Drive one always-warm stealth Chrome owned by the ultrastealth daemon. The browser starts once and stays warm; every command attaches in milliseconds. This is the Ultrastealth analogue of the cmux-browser skill — same mental model (navigate → snapshot → act → re-snapshot), but on real, bot-detection-passing Chrome with a persistent profile.

Prerequisite: the ultrastealth CLI is installed (ultrastealth --help) and, for the MCP path, the Ultrastealth MCP is connected. The daemon auto-starts on first use.

Golden rules (these ARE the speed wins)

Keep it warm. ultrastealth daemon start once. Every later command — CLI, MCP tool, or a connect() script — reuses the same browser: no cold Chrome start, shared cookies/session/cf_clearance.
Snapshot refs, not screenshots. ultrastealth browser snapshot --interactive --compact returns stable eN refs; act with click e2, type e5 --text "…". Re-snapshot after navigation or a DOM change. Screenshots are for human review only (like Playwright's opt-in vision mode).
Batch multi-step flows. Collapse navigate → wait → click → type → snapshot into ONE browser_batch (MCP) / ultrastealth browser batch (CLI) call instead of one action per turn.
--snapshot-after on a mutating action returns the fresh snapshot in the same response — no separate observe step.

Core loop (CLI, deterministic + fast)

ultrastealth daemon start
ultrastealth browser navigate https://example.com
ultrastealth browser snapshot --interactive --compact   # → [e0] <button> "Login" …
ultrastealth browser click e0 --snapshot-after
ultrastealth browser type e3 --text "[email protected]"
ultrastealth browser get title

Add --json for machine-readable output; --tab/--socket to target a specific daemon; --no-autostart to fail instead of starting one.

Core loop (agent via MCP)

Prefer browser_batch with a JSON step list and end with a snapshot step so you get refs back in one call. Use browser_snapshot to refresh refs; use browser_navigate/browser_click/browser_type for single actions. When a daemon is running, these MCP tools and the CLI drive the same warm browser.

Read the full file on GitHub · 94 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/commands.md 3.7 KB

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.

4d ago First seen · 94 lines · 96 tokens per session scan A 5cf737e5f136

Subscribe to this mod's changes

fast-browser is a skill published in the GitHub repository anusoft/ultrastealth (0 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,110 once invoked, about $0.0005 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.

Browser automation

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 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

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens