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 Edwardsaga/agent-stealth-browser --skill examplesgit clone --depth 1 https://github.com/Edwardsaga/agent-stealth-browserWrote 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/edwardsaga/agent-stealth-browser/examples)<a href="https://agentmods.dev/skills/edwardsaga/agent-stealth-browser/examples"><img src="https://agentmods.dev/badge/skills/edwardsaga/agent-stealth-browser/examples/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/edwardsaga/agent-stealth-browser/examples"><img src="https://agentmods.dev/badge/skills/edwardsaga/agent-stealth-browser/examples.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 | $0.00098 | $0.01065 |
| Opus 5.5 | $0.00039 | $0.00426 |
| Sonnet 5.5 | $0.00020 | $0.00213 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
agent-stealth-browser 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Stealth Browser
与 agent-browser 兼容的 Stealth 模式浏览器 MCP 工具。
MCP 配置
{
"mcpServers": {
"stealth-browser": {
"command": "uvx",
"args": ["agent-stealth-browser"]
}
}
}
核心工作流
- 导航:
browser_navigate {"url": "<url>"} - 快照:
browser_snapshot {}(返回带 @ref 的元素列表) - 交互: 使用快照中的 @ref 进行操作
- 页面变化后重新获取快照
工具列表
导航
browser_navigate {"url": "<url>"} # 导航到 URL
browser_close {} # 关闭浏览器
快照 (页面分析)
browser_snapshot {} # 获取可交互元素
browser_snapshot {"interactive_only": true} # 仅交互元素(默认)
交互 (使用快照中的 @ref)
browser_click {"target": "@e1"} # 点击
browser_fill {"target": "@e2", "text": "内容"} # 清空并填写
browser_type {"target": "@e2", "text": "内容"} # 逐字输入
browser_press {"key": "Enter"} # 按键
browser_hover {"target": "@e1"} # 悬停
browser_select {"target": "@e1", "value": "选项值"} # 下拉选择
browser_scroll {"direction": "down", "amount": 500} # 滚动
获取信息
browser_get {"what": "text", "target": "@e1"} # 获取文本
browser_get {"what": "html", "target": "@e1"} # 获取 HTML
browser_get {"what": "value", "target": "@e1"} # 获取输入值
browser_get {"what": "title"} # 获取标题
browser_get {"what": "url"} # 获取 URL
截图
browser_screenshot {} # 当前视口截图
browser_screenshot {"full_page": true} # 全页面截图
browser_screenshot {"selector": "@e1"} # 指定元素截图
等待
browser_wait {"ms": 2000} # 等待毫秒
browser_wait {"selector": ".success"} # 等待元素出现
Cookie 持久化
browser_cookies_save {"domain": "example"} # 保存登录状态
browser_cookies_load {"domain": "example"} # 加载登录状态
JavaScript
browser_eval {"script": "document.title"} # 执行 JS
示例: 表单提交
browser_navigate {"url": "https://example.com/form"}
browser_snapshot {}
# 输出: @e1 textbox "Email", @e2 textbox "Password", @e3 button "Submit"
browser_fill {"target": "@e1", "text": "[email protected]"}
browser_fill {"target": "@e2", "text": "password123"}
browser_click {"target": "@e3"}
browser_wait {"ms": 2000}
browser_snapshot {} # 检查结果
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 · 128 lines · 98 tokens per session scan A df3fc044e202
agent-stealth-browser is a skill published in the GitHub repository Edwardsaga/agent-stealth-browser (9 stars, last pushed 8mo ago), licensed MIT. It adds 98 tokens to every session and 1,065 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
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
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.