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-devgit 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-dev)<a href="https://agentmods.dev/skills/platonai/browser4/browser4-dev"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-dev/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-dev"><img src="https://agentmods.dev/badge/skills/platonai/browser4/browser4-dev.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 | $0.00084 | $0.02160 |
| Opus 5.5 | $0.00034 | $0.00864 |
| Sonnet 5.5 | $0.00017 | $0.00432 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade A, and why
browser4-dev 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser4-dev
Quick Start
Add a new browser4-cli command with one call:
coding.scaffoldFlow(type="b4-cli-command", name="my-command", verify=true)
scaffoldFlow generates the whole chain — commands.rs CommandDef, backend MCP alias, tool executor, and test — from a single name; verify=true runs the type-appropriate build check. For other work (agent tool, REST endpoint, test class, skill), use the matching type and see Workflows below.
Develop features inside the Browser4 repository itself, following the repository's own conventions (AGENTS.md) — with multi-file skeletons generated from the repository's real reference implementations, so the output never goes stale.
When to Use
- User wants to add a new
browser4-clicommand - User wants to add a new agent tool domain (plugin tool)
- User wants to add a REST endpoint (Controller + Service)
- User wants to add a test class or a skill
- User wants to modify Browser4's own Kotlin/Rust code and verify it compiles
- User wants to know which modules a change affects, or plan a whole dev task
How It Works
scaffoldFlow derives multi-file skeletons from the repository's real reference implementations, so generated code matches current conventions instead of stale templates. moduleGraph/impact rebuild the dependency picture from the live pom.xml files, and mvnBuild verifies with structured diagnostics. Follow AGENTS.md conventions at every step.
Patterns
1. Add a new CLI command
coding.scaffoldFlow(type="b4-cli-command", name="my-command", verify=true)
coding.mvnBuild(module="browser4-rest")
2. Add a REST endpoint
coding.scaffoldFlow(type="rest-endpoint", name="my-resource", verify=true)
3. Modify browser driver code
coding.trapCheck(path="browser4-core/browser4-browser/src/.../PulsarWebDriver.kt")
coding.impact(path=<file>)
coding.mvnBuild(module="browser4-core/browser4-browser")
Flags
coding tools take structured arguments, not CLI flags — see Workflows below for each tool's parameters.
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 · 203 lines · 84 tokens per session scan A 4c1fc7222360
browser4-dev is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 84 tokens to every session and 2,160 once invoked, about $0.0003 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.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.