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 nex-browser/nexbrowser-mcp --skill nexbrowser-automationgit clone --depth 1 https://github.com/nex-browser/nexbrowser-mcpWrote 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/nex-browser/nexbrowser-mcp/nexbrowser-automation)<a href="https://agentmods.dev/skills/nex-browser/nexbrowser-mcp/nexbrowser-automation"><img src="https://agentmods.dev/badge/skills/nex-browser/nexbrowser-mcp/nexbrowser-automation/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/nex-browser/nexbrowser-mcp/nexbrowser-automation"><img src="https://agentmods.dev/badge/skills/nex-browser/nexbrowser-mcp/nexbrowser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.02834 |
| Opus 5 | $0.00046 | $0.01417 |
| Sonnet 5 | $0.00018 | $0.00567 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
nexbrowser-automation 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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NexBrowser Automation Skill
Use this skill whenever the user names NexBrowser or needs to manage or automate a live NexBrowser session through the unified NexBrowser MCP tools.
When to Use
- The user explicitly says NexBrowser/nexbrowser, NexBrowser OpenAPI, “使用 NexBrowser”, “查看有多少窗口”, “查询环境”, or “浏览器环境”.
- The user wants to list or count managed NexBrowser windows/environments/profiles. Call
nex_browser_list; do not inspect Chrome, Edge, the Codex in-app browser, operating-system windows, processes, or tabs. - The user wants to control a browser: navigate, click, type, scroll, upload, or scrape.
- The task needs element targets from an accessibility snapshot.
- The task needs help diagnosing a browser-automation failure.
Quick Decision Matrix
| User intent | Tool | Notes |
|---|---|---|
| List/count environments | nex_browser_list |
NexBrowser managed windows only; never OS windows or tabs. |
| Import custom proxies | nex_proxy_import |
Only with proxy lines the user pasted in the current request; credentials are never returned. |
| Create or edit a proxy | nex_proxy_create, nex_proxy_batch_create, nex_proxy_modify, nex_proxy_delete, nex_proxy_detect |
Structured host/port create; delete is destructive. Credentials are never returned. |
| List proxies | nex_proxy_list |
Select a proxyId for create or bind; credentials are never returned. |
| Bind a proxy | nex_browser_bind_proxy |
Closed windows only; proxyId=0 removes the binding. |
| Manage window groups | nex_browser_group_list, nex_browser_group_create, nex_browser_group_modify |
Group 0 is the ungrouped bucket and cannot be renamed or deleted. |
| Manage platform accounts | nex_account_list, nex_account_create, nex_account_batch_create, nex_account_modify, nex_account_delete |
Workspace catalog only; secrets are never returned. Open-window vault fill still uses nex_browser_accounts. |
| Bind a platform account | nex_browser_bind_account |
Closed windows only; replaces the window binding. accountIds=[] removes it. |
| Create environments | nex_browser_create |
Desktop defaults fill every field you omit; only override on request. |
| Open environments | nex_browser_open |
Pass all target IDs in one array when opening multiple windows. |
| Connect to NexBrowser | nex_browser_connect |
Requires a managed window ID; the active team is used by default. |
| Navigate to a URL | nex_browser_navigate |
Use for an initial or explicitly supplied URL. |
| Inspect elements | nex_browser_snapshot |
Preferred over a screenshot for interaction. |
| Click, type, or select | nex_browser_click, nex_browser_type, nex_browser_select_option |
Use snapshot target values. |
| Sign in to a platform | nex_browser_accounts, nex_browser_fill_account, nex_browser_fill_credentials |
Prefer a stored vault credential; use literal values only when the user explicitly supplies or asks to use them. |
| Wait for a page change | nex_browser_wait_for |
Prefer text with timeout over fixed time. |
| Read structured data | nex_browser_evaluate |
Prefer UI tools for state-changing actions. |
| Inspect visual state | nex_browser_take_screenshot |
Use when layout or rendered media matters. |
| Debug failures | nex_browser_console_messages, nex_browser_network_requests |
Inspect after reproducing the issue. |
What ships with it
19 files 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.
- examples/aria-mode-workflow.md 655 B
- examples/connect-and-navigate.md 336 B
- examples/debugging-failed-automation.md 617 B
- examples/dynamic-content.md 444 B
- examples/file-upload.md 527 B
- examples/form-fill-submit.md 872 B
- examples/multi-tab-workflow.md 602 B
- examples/navigate-by-clicking.md 637 B
- examples/optimized-mode-workflow.md 557 B
- examples/scrape-data.md 398 B
- examples/sign-in-with-bound-account.md 1.9 KB
- examples/sign-in-with-literal-credentials.md 3.7 KB
- guides/error-handling.md 1.5 KB
- guides/human-like-interaction.md 1.1 KB
- guides/snapshot-modes.md 987 B
- guides/tool-selection.md 1.7 KB
- guides/waiting-and-timing.md 841 B
- README.md 648 B
- references/tool-catalog.md 12 KB
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.
- 8d ago First seen · 115 lines · 91 tokens per session scan A 9df966eb4335
nexbrowser-automation is a skill published in the GitHub repository nex-browser/nexbrowser-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 91 tokens to every session and 2,834 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…