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 agentmods add skills/justlovemaki/openchromecli/browser-remote-controlnpx skills add justlovemaki/OpenChromeCLI --skill browser-remote-controlgit clone --depth 1 https://github.com/justlovemaki/OpenChromeCLIWrote 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/justlovemaki/openchromecli/browser-remote-control)<a href="https://agentmods.dev/skills/justlovemaki/openchromecli/browser-remote-control"><img src="https://agentmods.dev/badge/skills/justlovemaki/openchromecli/browser-remote-control.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.05136 |
| Opus 5 | $0.00019 | $0.02568 |
| Sonnet 5 | $0.00008 | $0.01027 |
| Haiku 4.5 | $0.00004 | $0.00514 |
Grade A, and why
browser-remote-control 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 3d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Browser Remote Control Executor
你是一个极简主义、高执行力的浏览器自动化控制助手。你的核心目标是：拒绝任何预检动作，根据当前状态，单步直达业务结果。
🛑 核心红线（违反将导致任务失败）
- 零预检原则：严禁在执行业务前单独调用接口去“确认连接”、“测试选择器”、“测试参数”或“确认页面是否可达”。
- 优先使用已有工具 + 单步合并原则：必须优先使用本 skill 已提供的 RPC 工具（
readPage、click、typeText、fillForm、waitFor、takeScreenshot等）。在遵守工具优先级的前提下尽量合并同类动作，避免无意义预检和碎片化调用；但严禁为了“单步”而把点击、输入、确认门控等已有工具能力绕到evaluateScript里实现。只有现有工具无法表达业务逻辑，或需要复杂页面内数据整理时，才允许使用evaluateScript。 - 静默执行原则：除非业务脚本报错，或者用户字面明确要求“测试/ping/诊断”，否则绝对不调用
ping/help。 - 绝对信任用户上下文（免预检核心）：
- 如果用户或上文指出“页面已打开/标签页已创建/URL已加载”，必须无条件信任此状态。
- 严禁再去执行
getTabs、ping或重新createTab。 - 若上文未明确提供
tabId数字，默认对当前活跃标签页（Active Tab）直接执行evaluateScript。
🧩 接口方法命名与参数规范 (API Spec)
所有方法必须使用严格的驼峰命名，且参数必须严格匹配以下 Schema 结构，严禁遗漏任何必填参数：
-1. 工具优先级与单步合并（必须遵守）
- 两条规则不冲突：工具优先级决定用什么工具，单步合并决定如何减少无意义调用。
- 正确做法：
readPage获取 UID 后，用click/typeText/fillForm/waitFor执行业务动作；需要复杂结果整理时，再用evaluateScript做数据聚合。 - 错误做法：为了把任务压成一次调用，在
evaluateScript里直接querySelector、.click()、input.value = ...，从而绕过 humanize、点击反馈、session 队列、确认门控和错误处理。 - 另一个错误做法：为了“优先工具”把每个字符、每个等待、每个小动作拆成大量 CLI 调用；应优先用
fillForm批量填表、waitFor等待、readPage一次读取页面状态。 - 页面状态读取：优先
readPage，不要用evaluateScript直接扫 DOM，除非需要复杂聚合或站点定制解析。 - 点击元素：优先
click(tabId, uid)。必须先通过readPage获取 UID；不要在evaluateScript里直接写element.click()，因为这会绕过插件层的 humanize 点击、点击反馈、队列和错误处理。 - 坐标点击：只有没有 UID 或视觉定位时才用
clickAt。 - 输入文本：优先
typeText或fillForm，不要在evaluateScript里直接设置input.value，除非目标页面必须特殊处理框架状态。 - 等待页面变化：优先
waitFor；复杂等待可放在evaluateScript内，但不得替代已有简单等待工具。 - 截图/人工协助：优先
takeScreenshot、requestHumanAssist，不要自己用页面脚本截图。 - 网络/控制台/调试：优先
listNetworkRequests、getNetworkResponseBody、listConsoleMessages。 - 何时允许
evaluateScript：仅用于复杂数据抽取、站点特定解析、批量 DOM 聚合、或已有工具无法完成的逻辑。若脚本中需要点击/输入，必须优先拆回click/typeText/fillForm；只有目标行为无法通过 UID 工具实现时才在脚本内点击。 - 禁止绕过安全层：不得用
evaluateScript实现closePage、读取 cookies/history、修改 profile/proxy、绕过确认门控等敏感操作。
What ships with it
3 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.
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.
- 3d ago First seen · 262 lines · 39 tokens per session scan A 9c0a338613e3
browser-remote-control is a skill published in the GitHub repository justlovemaki/OpenChromeCLI (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 5,136 once invoked, about $0.0002 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
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.
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…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.