browser-automation

A browser-control toolkit for using a real web browser through automated clicks, typing, navigation, page reading, and screenshots.

In plain words
What is it for?
Use it to fill in forms, navigate websites, read page content, take screenshots, and test web interfaces.
Why use it?
It removes the need to perform repetitive browser tasks manually and helps test what users actually see and do on a website.

Skill for Claude CodeCodex

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/compnew2006/browser-controller/browser-automation
Any agent
npx skills add compnew2006/browser-controller --skill browser-automation
Clone the repo
git clone --depth 1 https://github.com/compnew2006/browser-controller

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 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 $0.00034 $0.01065
Opus 5 $0.00017 $0.00532
Sonnet 5 $0.00007 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 0a700028b2c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-automation 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 2d 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.

agent-config/skills/browser-automation/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with Browser Controller

Use this skill when you need to interact with the user's actual browser - clicking, typing, reading pages, taking screenshots, or navigating.

CRITICAL: Always target a tab explicitly (v2)

This is a multi-client server — other agents may be using other tabs. You MUST pass tabId to every page-interaction tool; actions never hit "the active tab" implicitly.

  1. First call browser_tabs with action: "list" to discover tabs and get a tabId
  2. Pass that same tabId to browser_snapshot, browser_click, browser_type, etc.
  3. Refs from a snapshot are valid only for the tabId that produced them — never reuse a ref from tab 10 on tab 20
  4. If you need exclusive use of a tab, browser_tabs { action: "lock", tabId } first, then unlock when done

If tabId is missing you'll get: "tabId is required. Call browser_tabs list first."

Before You Start

  1. Verify the extension is connected: browser_tabs { action: "list" } (returns the tab list)
  2. If disconnected, ask the user to check the extension icon (should show green "ON")
  3. Never close tabs you didn't create

If only browser_tools is visible (progressive mode)

The server hides tool definitions until needed (BROWSER_CONTROLLER_PROGRESSIVE=1). Use browser_tools { action: "list" } or { action: "search", query: "…" } to discover tools, then { action: "details", tool: "browser_click" } to get the schema and activate it. A "Tool X disabled" error means activate it via details first; once activated it stays callable for the session.

Reading Pages

browser_snapshot { tabId } returns the accessibility tree with refs like "e12" that you use for interaction.

For large pages, scope with a selector: browser_snapshot { tabId, selector: "main" }.

Use browser_text { tabId } to extract raw text when you need full content.

Reading efficiently (don't re-scan everything)

  • isNew: true on a ref means that element appeared since the last snapshot. When something just changed (an overlay opened after a click, a dropdown rendered), filter to isNew refs instead of re-reading the whole tree — big token saver on large pages.
  • After browser_scroll, expect refsMayBeStale: true — the feed may have recycled DOM nodes. Re-snapshot before your next interaction.

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 34 tokens per session scan A 0a700028b2c6

Subscribe to this mod's changes

browser-automation is a skill published in the GitHub repository compnew2006/browser-controller (1 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,065 once invoked, about $0.0002 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

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…

vercel-labs/agent-browser · 112 tokens

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

playwright

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.

XiaomiMiMo/MiMo-Code · 45 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

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens