Webwright is a browser-agent framework that gives language models a terminal for launching browser sessions, inspecting pages, and completing web tasks through rerunnable Python scripts. It helps coding agents perform long, multi-step browser tasks while recording the browsing procedure as code. Catalogue add-ons integrate Webwright with supported coding agents.
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.
git clone --depth 1 https://github.com/microsoft/WebwrightWrote 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/plugins/microsoft/webwright/marketplace)<a href="https://agentmods.dev/plugins/microsoft/webwright/marketplace"><img src="https://agentmods.dev/badge/plugins/microsoft/webwright/marketplace/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/plugins/microsoft/webwright/marketplace"><img src="https://agentmods.dev/badge/plugins/microsoft/webwright/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
webwright marketplace 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.
What it actually says
{
"name": "webwright",
"owner": {
"name": "Microsoft Research",
"url": "https://github.com/microsoft/Webwright"
},
"plugins": [
{
"name": "webwright",
"source": {
"source": "github",
"repo": "microsoft/Webwright"
},
"description": "Turn your coding agent into a SOTA browser agent. Drives a local Playwright workspace via one bash command at a time, saving screenshots and an action log into final_runs/run_<id>/, and visually self-verifies the result.",
"version": "0.1.0",
"category": "automation",
"keywords": ["browser", "playwright", "web-agent", "automation", "rpa"]
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file beside marketplace.json 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 · 21 lines scan A c96a329a5d65
webwright marketplace is a plugin published in the GitHub repository microsoft/Webwright (6,064 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
build-information
MCP configuration declaring 1 server: build-information.
kernel-sdks
TypeScript and Python SDK skills for building browser automation with Kernel's Typescript and Python SDKs.
realbrowser
Target-first local Chrome/Chromium browser control with signed-in profiles, labeled tabs, and guarded actions.
sniff
Autonomous QA scanner via sniff-qa: walks your running app in a real browser and reports real bugs (broken pages/links, console/network errors, broken forms, state-loss, empty/placeholder data, bad loading/error states, responsive + a11y) with reproduction proof, severity, confidence, and a fix. No API key.
rad-chrome-extension
MV3 Chrome extension development standards (WXT, React, TypeScript) with two pure-stdlib Python validators that catch what LLM eyeballing misses. Skills cover architecture, MV3 security (CSP, remote code ban, content script isolation), permission minimization and CWS compliance, typed messaging, storage selection…
headless
Headless browser automation for site comparison, E2E testing, and anti-bot-aware web research.