real-browser-mcp: Skill for Codex

.codex/skill/browser-automation/SKILL.md

browser-automation is a skill for Codex from ton-to-ton/real-browser-mcp. It costs 17 tokens per session (584 once invoked), scanned A, original, MIT.

A set of practices for automating web browsers through small, reusable actions such as opening pages, clicking controls, entering text, and selecting options.

In plain words
What is it for?
Use it to automate browsing workflows, reproduce selector or scrolling problems, and debug browser tools from the command line.
Why use it?
It helps make browser tasks more dependable by checking the page before acting and confirming that each action changed the expected state.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions Codex.

This is ton-to-ton/real-browser-mcp's own configuration. It tells Codex how to work on real-browser-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything real-browser-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ton-to-ton/real-browser-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ton-to-ton/real-browser-mcp/main/.codex/skill/browser-automation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ton-to-ton/real-browser-mcp

Made for: 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 browser-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/ton-to-ton/real-browser-mcp/browser-automation/github.svg)](https://agentmods.dev/skills/ton-to-ton/real-browser-mcp/browser-automation)
Your own site
<a href="https://agentmods.dev/skills/ton-to-ton/real-browser-mcp/browser-automation"><img src="https://agentmods.dev/badge/skills/ton-to-ton/real-browser-mcp/browser-automation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for browser-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/ton-to-ton/real-browser-mcp/browser-automation"><img src="https://agentmods.dev/badge/skills/ton-to-ton/real-browser-mcp/browser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 584 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.00584
Opus 5 $0.00009 $0.00292
Sonnet 5 $0.00003 $0.00117
Haiku 4.5 $0.00002 $0.00058

Measured 10d ago against content hash 47e49fe0f42f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 10d 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.

.codex/skill/browser-automation/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

  • Provide a safe, composable workflow for browsing tasks
  • Use browser_query list and index selection to click reliably
  • Confirm state changes after each action
  • Support CLI-first debugging with codex-browser tool commands

Best-practice workflow

  1. Inspect tabs with browser_get_tabs
  2. Open new tabs with browser_open_tab when needed
  3. Navigate with browser_navigate if needed
  4. Wait for UI using browser_query with timeoutMs
  5. Discover candidates using browser_query with mode=list
  6. Click, type, or select using index
  7. Confirm using browser_query or browser_snapshot

CLI-first debugging

  • List all available tools: npx codex-browser tools
  • Run one tool directly: npx codex-browser tool browser_status
  • Pass JSON args: npx codex-browser tool browser_query --args '{"mode":"page_text"}'
  • Run smoke test: npx codex-browser self-test
  • After update, reload the unpacked extension in chrome://extensions

This path is useful for reproducing selector and scroll issues quickly before running a full Codex session.

Selecting options

  • Use browser_select for native <select> elements
  • Prefer value or label; use optionIndex when needed
  • Example: browser_select({ selector: "select", value: "plugin" })

Query modes

  • text: read visible text from a matched element
  • value: read input values
  • list: list many matches with text/metadata
  • exists: check presence and count
  • page_text: extract visible page text

Opening tabs

  • Use browser_open_tab to create a new tab, optionally with url and active
  • Example: browser_open_tab({ url: "https://example.com", active: false })

Troubleshooting

  • If a selector fails, run browser_query with mode=page_text to confirm the content exists
  • Use mode=list on broad selectors (button, a, *[role="button"], *[role="listitem"]) and choose by index
  • For inbox or chat panes, try text selectors first (text:Subject line) then verify selection with browser_query
  • For scrollable containers, pass both selector and x or y to browser_scroll and then verify scrollTop
  • Confirm results after each action

Read the full file on GitHub · 64 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. 10d ago First seen · 64 lines · 17 tokens per session scan A 47e49fe0f42f

Subscribe to this mod's changes

browser-automation is a skill published in the GitHub repository ton-to-ton/real-browser-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 584 once invoked, about $0.0001 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

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 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

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

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 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