Browser4 is an AI-native browser engine that lets autonomous agents and people control real browsers, extract information from web pages, and automate tasks at scale. It combines browser interaction through a Rust CLI and MCP with deterministic selectors, machine-learning clustering, and language-model extraction. The catalogue entries provide skills and instructions for using Browser4.
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.
npx skills add platonai/Browser4 --skill browser4-seogit clone --depth 1 https://github.com/platonai/Browser4Wrote 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.
[](https://agentmods.dev/skills/platonai/browser4/browser4-seo)<a href="https://agentmods.dev/skills/platonai/browser4/browser4-seo"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-seo/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.
<a href="https://agentmods.dev/skills/platonai/browser4/browser4-seo"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00057 | $0.01540 |
| Opus 5.5 | $0.00023 | $0.00616 |
| Sonnet 5.5 | $0.00011 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
browser4-seo 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser4 SEO
Quick Start
browser4-cli goto "https://example.com" # load the page to audit
browser4-cli plugin-list # confirm browser4-seo is installed AND enabled
# then call seo.extractMeta() — full SEO metadata extraction (see Tools below)
Extract and audit SEO metadata from the current page using the browser4-seo plugin's two tools.
When to Use
Use this skill when the user wants to:
- Check a page's SEO health — "audit the SEO of this page", "is this page SEO-friendly?"
- Review meta tags — "what's the title/description/canonical of this page?"
- Check Open Graph / Twitter Card — "does this page have proper social share tags?"
- Review structured data — "does this page have JSON-LD schema markup?"
- Diagnose ranking problems — "why isn't this page ranking?" (SEO issues are a common cause)
Do NOT use this skill for:
- General content extraction — use the
browser4-cliHTML snapshot / X-SQL instead. - Performance auditing (Core Web Vitals) — this plugin only covers SEO metadata, not performance metrics.
How It Works
The browser4-seo plugin exposes two tools that operate on the page currently loaded in the browser session: seo.extractMeta() returns every SEO metadata field (title, description, canonical, Open Graph, Twitter Cards, JSON-LD), and seo.checkIssues() compares the page against SEO best practices and returns a health report.
Patterns
1. Quick SEO health check
seo.checkIssues() # returns a prioritized issue list
2. Full metadata extraction
seo.extractMeta() # all fields: title, description, canonical, OG, Twitter, JSON-LD
3. Diagnose poor ranking
seo.checkIssues() # start with the issue report, then fix the top items
Flags
Neither seo.extractMeta() nor seo.checkIssues() takes arguments — both operate on the page currently loaded in the browser session.
Errors & Recovery
| Symptom | Cause | Fix |
|---|---|---|
| Tool call fails with "plugin not found" | browser4-seo not installed |
browser4-cli plugin-list; install the plugin |
Plugin installed but seo.* tools unavailable |
Plugin is opt-in (default-disabled) | Enable it: browser4.plugins.enable=browser4-seo (or browser4.plugins.enable-all=true) and restart |
extractMeta returns empty fields |
No page loaded in the session | browser4-cli goto <url> first |
checkIssues reports everything missing |
Page is a JS shell | The plugin reads the loaded DOM — ensure the page finished rendering |
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.
- 1mo ago Changed · +1 lines b057752b7efe
- 1mo ago First seen · 158 lines · 57 tokens per session scan A 2a1849934e47
browser4-seo is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 1,540 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
eric-task-master
Run durable local Chrome automation with the installed Task Master CLI. Use when an Agent needs to create and execute a one-off browser task, follow its progress, or manage its Chrome Profile.
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.