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-codinggit 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-coding)<a href="https://agentmods.dev/skills/platonai/browser4/browser4-coding"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-coding/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-coding"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 22 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 190 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 191 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00088 | $0.03281 |
| Opus 5.5 | $0.00035 | $0.01312 |
| Sonnet 5.5 | $0.00018 | $0.00656 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade A, and why
browser4-coding 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser4-coding
Quick Start
Create and validate a plugin, or a skill:
coding.scaffold(type="plugin", pluginName="My Plugin", domain="media",
basePackage="ai.platon.pulsar.myplugin",
toolMethod="detectMedia", toolDescription="Detect media on the page")
coding.validate(type="plugin", path="browser4-plugins/browser4-myplugin")
coding.scaffold(type="skill", name="my-skill", description="What it does")
coding.validate(type="skill", path="skills/my-skill/SKILL.md")
For self-development work (modifying Browser4 itself), start with coding.scaffoldFlow — see Workflows below.
The programming-agent kernel for Browser4: sandboxed shell + filesystem, artifact scaffolding/validation (plugins, skills, browser JS, scripts), and a full self-development toolset for modifying Browser4's own code (live module graph, impact analysis, Maven builds with structured diagnostics, CDP pitfall awareness, high-level dev-task planning).
When to Use
- User wants to create a new Browser4 plugin, skill (SKILL.md), browser JS script, or build/deploy/run script
- User wants to validate any of the above
- User wants to modify Browser4's own code (Kotlin modules, Rust CLI, poms) — use the self-development tools below
- User wants to check repo governance (versions, module registration) or the CDP pitfalls before editing the browser driver
How It Works
The coding tools fall into three layers: artifact tools generate and validate plugins, skills, JS, and scripts (templates from real code so they never go stale); self-development tools inspect and modify Browser4 itself (live module graph, impact analysis, Maven builds, CDP trap checks); and shell/filesystem tools provide a sandboxed environment for anything else.
Patterns
1. Create and validate a new plugin
coding.scaffold(type="plugin", pluginName="...", domain="...", basePackage="...", toolMethod="...", toolDescription="...")
coding.validate(type="plugin", path="browser4-plugins/browser4-xxx")
coding.mvnBuild(module="browser4-plugins/browser4-xxx")
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 First seen · 210 lines · 88 tokens per session scan A faab6af06f5a
browser4-coding is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 3,281 once invoked, about $0.0004 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.