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 weathergit 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/weather)<a href="https://agentmods.dev/skills/platonai/browser4/weather"><img src="https://agentmods.dev/badge/skills/platonai/browser4/weather/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/weather"><img src="https://agentmods.dev/badge/skills/platonai/browser4/weather.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 | $0.00051 | $0.01082 |
| Opus 5.5 | $0.00020 | $0.00433 |
| Sonnet 5.5 | $0.00010 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
weather 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weather Skill
Description
Use this skill when a user needs current weather conditions or a 7-day forecast for a named location. The bundled script resolves the location with Open-Meteo geocoding, fetches live forecast data without an API key, and returns normalized JSON that is easy to summarize or quote directly.
Dependencies
None
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| location | String | Yes | - | Free-form location such as Seattle, WA, London, or Tokyo |
| units | String | No | metric | Unit system: metric for Celsius and km/h, or imperial for Fahrenheit and mph |
| countryCode | String | No | - | Optional ISO 3166-1 alpha-2 country code to disambiguate places such as US, GB, or JP |
Return Value
The script prints JSON with the following shape:
{
"query": {
"location": "Seattle, WA",
"units": "imperial",
"countryCode": "US"
},
"resolvedLocation": {
"name": "Seattle",
"admin1": "Washington",
"country": "United States",
"countryCode": "US",
"latitude": 47.61,
"longitude": -122.33,
"timezone": "America/Los_Angeles"
},
"current": {
"time": "2026-04-09T09:00",
"summary": "Partly cloudy",
"temperature": 55.4,
"temperatureUnit": "degF",
"feelsLike": 53.8,
"humidity": 68,
"humidityUnit": "%",
"precipitation": 0.0,
"precipitationUnit": "inch",
"windSpeed": 7.1,
"windSpeedUnit": "mph",
"windDirection": 220,
"windDirectionUnit": "deg"
},
"forecast": [
{
"date": "2026-04-09",
"summary": "Partly cloudy",
"temperatureMax": 58.1,
"temperatureMin": 45.3,
"temperatureUnit": "degF",
"precipitationProbabilityMax": 24,
"precipitationProbabilityUnit": "%",
"precipitationSum": 0.02,
"precipitationSumUnit": "inch",
"windSpeedMax": 12.4,
"windSpeedUnit": "mph",
"sunrise": "2026-04-09T06:31",
"sunset": "2026-04-09T19:48"
}
],
"source": {
"provider": "Open-Meteo",
"forecastDays": 7
}
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 139 lines · 51 tokens per session scan A b1bd5f52ae5f
weather is a skill published in the GitHub repository platonai/Browser4 (1,161 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 1,082 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.
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.