What is browser-remote-control?

A set of instructions for controlling a real web browser through the Agent Browser Bridge command-line tool. It covers reading pages, navigating, clicking, typing, filling forms, waiting, and taking screenshots.

Automating websites, extracting page information, entering form data, clicking controls, navigating pages, and capturing screenshots.

It gives an AI agent a defined way to carry out browser tasks while avoiding unnecessary connection checks and fragmented actions.

browser-remote-control — Skill by justlovemaki/OpenChromeCLI

Install

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.

Any agent

npx skills add justlovemaki/OpenChromeCLI --skill browser-remote-control

Clone the repo

git clone --depth 1 https://github.com/justlovemaki/OpenChromeCLI

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/justlovemaki/openchromecli/browser-remote-control/github.svg)](https://agentmods.dev/skills/justlovemaki/openchromecli/browser-remote-control)

Your own site

<a href="https://agentmods.dev/skills/justlovemaki/openchromecli/browser-remote-control"><img src="https://agentmods.dev/badge/skills/justlovemaki/openchromecli/browser-remote-control/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,136 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.05136
Opus 5.5	$0.00016	$0.02054
Sonnet 5.5	$0.00008	$0.01027
Haiku 4.5	$0.00004	$0.00514

Measured 2mo ago against content hash 9c0a338613e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/cli.js, scripts/launch-fingerprint-browser.js, scripts/read-login-env.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/browser-remote-control/SKILL.md · 262 lines

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。

Read the full file on GitHub · 262 lines

Files

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.

Changes

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.

2mo ago First seen · 262 lines · 39 tokens per session scan A 9c0a338613e3

Subscribe to this mod's changes

browser-remote-control is a skill published in the GitHub repository justlovemaki/OpenChromeCLI (7 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 5,136 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 2026-08-31.

Browser automation

browser-remote-control next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browser-remote-controljustlovemaki/OpenChromeCLI	Skill	7	4mo ago	MIT	A	39	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	yesterday	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	yesterday	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	yesterday	MIT	A	40	Claude Code