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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/platonai/Browser4npx agentmods add skills/platonai/browser4/run-testsWrote 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/run-tests)<a href="https://agentmods.dev/skills/platonai/browser4/run-tests"><img src="https://agentmods.dev/badge/skills/platonai/browser4/run-tests/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/run-tests"><img src="https://agentmods.dev/badge/skills/platonai/browser4/run-tests.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 | $0.00044 | $0.02005 |
| Opus 5.5 | $0.00018 | $0.00802 |
| Sonnet 5.5 | $0.00009 | $0.00401 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
run-tests 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 14d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Tests
Two test entrypoints:
-
bin/test.ps1— unified test orchestrator for the Browser4 monorepo. Supports Maven tests, Rust CLI tests, PowerShell*.tests.ps1files, real-world scenario agent evaluations, and mock-server launch. -
bin/test-production.ps1— acceptance test for the latest production release of browser4-cli. Downloads, installs, exercises, uninstalls, and re-installs the global CLI from the public OSS distribution channel.
When to Use
- "run the tests"
- "run fast / unit tests"
- "run integration / it tests"
- "run e2e tests"
- "run cli tests"
- "run all PowerShell tests"
- "run real-world scenarios"
- "check what tests would run" (-DryRun / -Show)
- "resume failed tests"
- "launch mock server"
- "run production acceptance test"
- "acceptance test the latest release"
How It Works
bin/test.ps1 buckets test-type arguments into dispatch categories (Maven, CLI,
PowerShell, RWS, server) and runs each in sequence. The script must be invoked
from the repository root (it Set-Locations there automatically).
Test results are persisted per invocation to .test-sessions/<session-id>/test-session.json
(see bin/common/test-session.psm1). Pass -NoSession to skip persistence or -SessionPath
to write to a custom location.
Usage
./bin/test.ps1 [OPTIONS] [TEST-TYPES...] [EXTRA-ARGS...]
Options
| Flag | Description |
|---|---|
-DryRun |
Compile only (test-compile), do not run tests |
-Show |
Print the final command, do not execute anything |
-NoSession |
Skip persisting test results to .test-sessions/ |
-SessionPath <path> |
Custom path for the test-session JSON file |
Test Types
| Type | Category | Description |
|---|---|---|
fast |
Maven | Fast unit tests |
it |
Maven | Integration tests (-DrunITs=true) |
e2e |
Maven | End-to-end tests (-DrunE2ETests=true) |
rest |
Maven | REST module tests (-DrunRestTests=true) |
skills |
Maven | Skills-focused agentic tests (browser4-agentic) |
mcp |
Maven | MCP-focused agentic tests (browser4-agentic) |
main |
Maven | All Browser4 main tests: fast + it + e2e + rest |
cli |
CLI | Rust Browser4 CLI tests (cargo test --test e2e). Alias: browser4-cli |
ps |
PowerShell | All *.tests.ps1 files in the project |
resume |
Maven | Resume from the last failed module (-rf) |
mock-site |
Server | Launch MockSiteBoot (aliases: server, mocksite) |
rws |
RWS | Real-world scenario agent evaluations. Bare rws shows help; pass --scenarios or --task to run. |
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.
- 14d ago Changed 245edecd0287
- 1mo ago First seen · 229 lines · 44 tokens per session scan A 747630abd392
run-tests is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 2,005 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
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…