Agent Browser
quran/quran.com-frontend-next
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
使用 agent-browser-cli 进行浏览器感知与控制、页面交互、截图/PDF、Cookie/CDP 和排障. An agent skill from sleepinginsummer/agent-browser-cli.
Install Agent Browser CLI
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cli --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-browser-cli .claude/skills/agent-browser-cli && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .claude/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cliType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cli --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-browser-cli .agents/skills/agent-browser-cli && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .agents/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cli --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-browser-cli .cursor/skills/agent-browser-cli && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .cursor/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sleepinginsummer/agent-browser-cli.git --path skills/agent-browser-cli--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cli --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-browser-cli .gemini/skills/agent-browser-cli && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .gemini/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cliInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-browser-cli .github/skills/agent-browser-cli && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .github/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sleepinginsummer/agent-browser-cli agent-browser-cli --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sleepinginsummer/agent-browser-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-browser-cli .opencode/skills/agent-browser-cli && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-browser-cli" agent skill from https://github.com/sleepinginsummer/agent-browser-cli/tree/main/skills/agent-browser-cli into .opencode/skills/agent-browser-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-browser-cli", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-browser-cli- GitHub stars
- 630
- Token cost
- ~2.3k tokens
- SKILL.md length
- 393 words
- Files
- 2 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
使用 agent-browser-cli 进行浏览器感知与控制、页面交互、截图/PDF、Cookie/CDP 和排障. An agent skill from sleepinginsummer/agent-browser-cli.
- Tasks that involve Browser automation
- SKILL.md covers 正常流程直接执行命令, 打开本地文件, 常用命令优先级 and 端口和扩展, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agent Browser CLI is an agent skill from sleepinginsummer/agent-browser-cli. 使用 agent-browser-cli 进行浏览器感知与控制、页面交互、截图/PDF、Cookie/CDP 和排障。
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/operations.md`).
It sits in Productivity & Automation, covering Browser automation. The repository describes itself as: 使用 agent-browser-cli 进行浏览器感知与控制。适用于标签页扫描/切换、页面 JS 执行、Cookie、CDP、contentSettings、截图、文件上传、下拉框点击、tmwdcdpbridge 初始化和 Web 工具排障. The licence is MIT.
When your agent uses it
- Tasks that involve Browser automation
Example prompts
- “/agent-browser-cli”
What it can do on your machine
Read from SKILL.md and the folder at commit 0194051. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Browser CLI loads about 2.3k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 19 tokens; SKILL.md has 393 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from sleepinginsummer/agent-browser-cli at commit 0194051, republished under its MIT licence (© sleepinginsummer). 393 words, ~2,340 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-browser-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- agent-browser-cli
- description
- 使用 agent-browser-cli 进行浏览器感知与控制、页面交互、截图/PDF、Cookie/CDP 和排障。
agent-browser-cli
使用 agent-browser-cli 控制用户真实 Chrome。底层是 Rust daemon + Chrome 扩展桥，保留登录态和 Cookie；不是 Selenium/Playwright。
正常流程直接执行命令
每次开始浏览器任务，不要先做健康检查，直接执行最贴近目标的命令。tabs / open / exec / scan 会按需自动启动 daemon；daemon 未常驻是正常状态，不是故障。
agent-browser-cli open https://example.com
agent-browser-cli scan --text-only
agent-browser-cli snapshot --limit 200
agent-browser-cli exec --tab <tabId> 'return document.title'只有目标命令失败、输出明确提示连接异常、扩展未连接、端口不一致、无可用标签页，或用户明确要求排障时，才进入状态检查：
agent-browser-cli status
agent-browser-cli doctor
agent-browser-cli logs --tail 100status 中 daemon_not_running / running=false 不能单独作为停止操作的理由；优先继续执行目标命令让 CLI 自动拉起 daemon。doctor 只检查状态，不自动启动 daemon、不改配置、不安装 skill。
补充一个容易误判的点：status / doctor 里看到 daemon_not_running，如果此时还没有执行 tabs / open / exec / scan，通常只是 daemon 按需常驻而未启动，不代表故障。只有目标命令已经失败，或者日志/输出明确提示端口、扩展、标签页异常时，才进入排障。
打开本地文件
open 支持 HTTP(S) URL、绝对 file:// URL 和本机文件路径。相对路径以执行 CLI 时的当前目录为基准；支持 ~、中文、空格和符号链接，符号链接会解析到真实文件。所有普通文件类型均可打开，目录会被拒绝。
agent-browser-cli open ./demo.html
agent-browser-cli open ~/Documents/report.pdf
agent-browser-cli open 'file:///Users/me/My%20Files/demo.html#intro'
agent-browser-cli open ./demo.html --timeout 15本地文件要求 Chrome 扩展版本至少为 2.1，并在 chrome://extensions → Agent Browser CLI Bridge → 详情中开启“允许访问文件网址”。权限关闭时 open 会在创建标签前失败；status / doctor 会按 Profile 报告 file_scheme_access，但该可选能力不影响普通 HTTP(S) 健康状态。
输入分类规则：
./、../、~/、绝对路径和显式file://表示本地文件；文件必须存在且是普通文件。- 裸输入若对应当前目录中已存在的文件，文件优先；否则按 Web 地址处理。要强制打开网站，显式写
https://。 - 普通路径中的
?和#是文件名字符；仅显式file://URL 使用 query/fragment 语义。 localhost、回环/私网 IP、单标签主机和.local的无协议地址默认使用 HTTP；其他域名默认 HTTPS；端口 80/443 分别强制 HTTP/HTTPS。- 只支持
http:、https:和file:；其他显式 scheme 会返回unsupported_scheme。 - 异平台路径会明确报错，例如 macOS/Linux 不会把
C:\\Users\\...错当作网址。
本地文件 open 默认最多等待 10 秒，直到新标签成为可控制会话；可用 --timeout 调整。超时后标签会保留，错误结果包含稳定的 error_code 和 opened_tab_id。活动 open 成功后新标签成为默认会话，--background 不切换默认会话。
常用命令优先级
先区分三个入口：
scan：内容感知，适合看正文、列表、页面文本。
snapshot：操作定位，适合找按钮、链接、输入框并生成 @e 引用。
exec / JSON CDP：逃生口，封装命令失效或特殊页面时回退。基础感知和按需排障：
agent-browser-cli tabs
agent-browser-cli tabtree
agent-browser-cli tabtree --full
agent-browser-cli tabtree --profile work
agent-browser-cli tabtree --tab <tabId>
agent-browser-cli lookup tab <tabId>
agent-browser-cli lookup browser <browser_id>
agent-browser-cli lookup profile work
agent-browser-cli tabs --profile work
agent-browser-cli profile-label set work --profile <profile_id>
agent-browser-cli scan --tabs-only
agent-browser-cli scan --profile work --tab <tabId> --text-only
agent-browser-cli open --profile work https://example.com
agent-browser-cli open --window https://example.com
agent-browser-cli open --window --focus https://example.com
# open 返回后继续操作新页面时，优先使用 result.opened_tab_id / result.opened_session_key
agent-browser-cli open https://example.com
agent-browser-cli close --tab <tabId>
agent-browser-cli exec --tab <tabId> 'return document.title'
agent-browser-cli status
agent-browser-cli doctor
agent-browser-cli logs --tail 100第二阶段后的推荐流程：
看页面内容：scan / scan --text-only
selector 明确时：直接 click/fill selector
selector 不明确或页面复杂时：snapshot 生成 @e，再 click/fill @e
页面结构或内容变化后：重新 snapshot
封装命令失效或覆盖不到特殊页面时：回退 exec / JSON CDP / 自定义 JS示例：
agent-browser-cli scan --text-only
agent-browser-cli click 'button[type=submit]'
agent-browser-cli snapshot --limit 200
agent-browser-cli snapshot --offset 200 --limit 200
agent-browser-cli snapshot --details
agent-browser-cli click '@e1'
agent-browser-cli fill '@e2' 'hello'
agent-browser-cli fill '@e2' --clear
agent-browser-cli fill '@e2' ' world' --append
agent-browser-cli send-keys --target '@e2' 'Enter'
agent-browser-cli mouse-click '@e3'所有高层操作都支持 --tab <tabId>，多 Chrome Profile / 多浏览器实例时还支持 --profile <profile_id-or-label> 和 --browser <browser_id>。tabs 输出会包含 browser_id、profile_id、profile_label、tab_id、session_key。tabtree 用树形结构列出 browser → profile → tabs，支持 --tab <tabId>、--profile <profile_id-or-label>、--browser <browser_id> 过滤，过滤结果仍保留父子节点；默认 compact 输出会截断 URL 并省略 session_key，需要完整字段时用 tabtree --full；lookup tab <tabId> 可由 tab 反查 browser_id / profile_id / profile_label，lookup browser <browser_id> 可反查所属 profile。profile-label set <label> --profile <profile_id> 可设置当前 Chrome Profile 的 label 并校验当前 daemon 内唯一性，profile-label clear --profile <profile_id> 可清空；popup 设置是本地便捷入口，不保证跨 Profile 唯一；label 只允许英文、数字、-、_、.，当前 daemon 内匹配到多个 profile 时会报歧义，不能猜。只传 --tab 且存在歧义时，必须补 --profile 或 --browser。@e 只在当前 daemon、当前 session_key、最近一次 snapshot 内有效。@e 只接受 @e1 这种带 @ 的格式。
慢页面要把等待和监控分开：
agent-browser-cli click '@e1' --wait-js 'return document.body.innerText.includes("完成")' --wait-timeout 10 --monitor--wait-js 负责等慢加载；--monitor 只负责操作前后页面 diff，默认关闭。
Chrome 右上角“正在控制你的浏览器”是 chrome.debugger.attach 的正常提示，不是 daemon 常驻状态。普通 CDP 命令空闲后会延迟约 30 秒自动 detach；30 秒内同一 tab 继续执行 CDP 会复用连接并重新计时。network/console 持续监听期间不会自动 detach，停止监听或清理时才释放。
弹窗处理：扩展默认不改写业务页面的 alert / confirm / prompt。只有 CLI 页面执行命令期间临时抑制弹窗，结束后恢复；如果怀疑页面原生弹窗行为异常，先让用户重载扩展和页面。
Show full SKILL.md (159 more words)Show less
端口和扩展
固定 API 端口：
127.0.0.1:18767默认扩展 WebSocket 端口：
127.0.0.1:18765配置文件：
~/.agent-browser-cli/config.json修改扩展端口会影响 Chrome 扩展和 daemon 连接，执行前必须说明影响并取得用户确认：
agent-browser-cli set-extension-port <port>网络和控制台调试
network / console 需要扩展侧持续监听 CDP 事件。修改或升级扩展后，必须先让用户重载 Chrome 插件。
agent-browser-cli network start --tab <tabId>
agent-browser-cli network list --tab <tabId> --filter api
agent-browser-cli network detail <requestId> --tab <tabId>
agent-browser-cli network clear --tab <tabId>
agent-browser-cli network stop --tab <tabId>
agent-browser-cli console start --tab <tabId>
agent-browser-cli console list --tab <tabId>
agent-browser-cli console list --tab <tabId> --level error
agent-browser-cli console clear --tab <tabId>
agent-browser-cli console stop --tab <tabId>network detail 会截断大响应体并标记 base64Encoded，不要把巨大 body 粘到对话里。network clear 清请求缓存；network stop 会停止监听并清请求缓存。console clear 清日志缓存；console stop 会停止监听并清日志缓存。
agent-browser-cli stop / daemon idle 退出时会额外清理 daemon 内的 snapshot/@e 缓存，并通知扩展清理 network/console 调试缓存。
标签分组
多任务开新标签时可以用 session 或 group-title 把标签放入 Chrome 原生标签组。需要独立窗口时用 open --window；默认不聚焦，需要抢焦点时显式加 --focus；--window --group-title / --window --session 会把新窗口里的首个 tab 加入对应 tab group。分组只是整理浏览器标签，失败不影响开 tab 主流程。
agent-browser-cli open https://example.com --session research
agent-browser-cli open https://example.com --group-title "任务A"
agent-browser-cli open --window https://example.com
agent-browser-cli open --window --focus https://example.com
agent-browser-cli open --profile work https://example.com--session 和 --group-title 都会作为标签组标题；两者同时传时优先使用 --group-title。
截图和 PDF
截图/PDF 必须让 CLI 写文件，不要把 base64 大段塞进上下文。命令只返回路径、字节数和少量元信息。
agent-browser-cli screenshot --out /tmp/page.png
agent-browser-cli screenshot --full-page --out /tmp/full.png
agent-browser-cli screenshot --target '@e1' --out /tmp/button.png
agent-browser-cli screenshot --selector 'button[type=submit]' --format jpeg --quality 70 --out /tmp/button.jpg
agent-browser-cli save-pdf --out /tmp/page.pdf
agent-browser-cli save-pdf --paper a4 --landscape --scale 0.9 --out /tmp/page.pdfscreenshot 默认截当前视口；--full-page 截全页；--target 和兼容别名 --selector 二选一，目标既可以是 @e 也可以是 CSS selector。没有 --out 时，截图写到 /tmp/agent-browser-cli-screenshots/。
save-pdf 默认 paper=a4、scale=1.0、print-background=true；需要关闭背景时用 --no-print-background。没有 --out 时，PDF 写到 /tmp/agent-browser-cli-pdfs/，默认文件名来自清理后的页面标题。
如果封装命令失效，用 exec 调 CDP 后由脚本落盘，仍然避免把 base64 粘到对话里。
exec 使用规则
执行复杂 JS 时写入临时文件：
agent-browser-cli exec --tab <tabId> --file /tmp/script.js需要等待页面变化时使用 --wait-js，不要在脚本里固定 setTimeout：
agent-browser-cli exec --tab <tabId> 'document.querySelector("button").click()' --wait-js 'return document.body.innerText.includes("完成")' --wait-timeout 3exec 中使用 await 必须显式 return，否则结果可能是 null。
JSON/CDP 逃生口
跨标签页、Cookie、CDP、扩展管理、浏览器内容权限时，用 JSON 指令：
agent-browser-cli exec '{"cmd":"tabs"}'
agent-browser-cli exec '{"cmd":"cookies"}'
agent-browser-cli exec '{"cmd":"cdp","tabId":303987837,"method":"Page.captureScreenshot","params":{"format":"png"}}'CDP 点击优先三事件序列：mouseMoved -> mousePressed -> mouseReleased。首次 attach 可能出现 Chrome infobar，先发无害 mouseMoved(0,0) 预热。
文件上传
文件上传优先用 DataTransfer API，不优先使用 CDP DOM.setFileInputFiles：
const input = document.querySelector('input[type=file]');
const file = new File(['content'], 'demo.txt', { type: 'text/plain' });
const dt = new DataTransfer();
dt.items.add(file);
input.files = dt.files;
input.dispatchEvent(new Event('input', { bubbles: true }));
input.dispatchEvent(new Event('change', { bubbles: true }));
return input.files.length;运维入口
- 目标命令失败、扩展未连接、端口不一致、无可用标签页：看
references/operations.md。 - daemon 未运行但尚未执行目标命令：不要排障，直接继续执行
tabs/open/exec/scan。 - skill 安装：先
agent-browser-cli install-skill --dry-run展示计划，用户确认后再agent-browser-cli install-skill。 - 可自动执行的排障命令：
status、doctor、logs --tail、restart、stop、tabs。
© sleepinginsummer, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in skills/agent-browser-cli of sleepinginsummer/agent-browser-cli.
- SKILL.md
- references/operations.md
Open the folder on GitHubat commit 0194051
Compare with similar skills
Agent Browser CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Browser CLI this skillsleepinginsummer/agent-browser-cli | 630 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Agent Browserquran/quran.com-frontend-next | 1.9k | 42 repos | ~3.3k | Automated safety check: Pass | None | |
| Dev-Browser CLI AutomationSawyerHood/dev-browser | 6.7k | 1 repos | ~455 | Automated safety check: Pass | MIT | |
| Agent Browsersuperagent-ai/grok-cli | 3.5k | 1 repos | ~633 | Automated safety check: Pass | MIT | |
| Browser Automationopenclaw/openclaw | 392k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Camoufox CLIBin-Huang/camoufox-cli | 350 | 1 repos | ~4.5k | Automated safety check: Pass | MIT |
Similar skills
Dev-Browser CLI Automation
SawyerHood/dev-browser
Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web…
Agent Browser
superagent-ai/grok-cli
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
Browser Automation
openclaw/openclaw
A skill your agent uses when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
Camoufox CLI
Bin-Huang/camoufox-cli
Anti-detect browser automation CLI & Skills for AI agents. An agent skill from Bin-Huang/camoufox-cli.
Browser
VibiumDev/vibium
Automate browsers with the Vibium CLI. An agent skill from VibiumDev/vibium.
Related
Categories
Questions about Agent Browser CLI
What does Agent Browser CLI do?
使用 agent-browser-cli 进行浏览器感知与控制、页面交互、截图/PDF、Cookie/CDP 和排障. An agent skill from sleepinginsummer/agent-browser-cli. Agent Browser CLI is an agent skill from sleepinginsummer/agent-browser-cli.
When should I use Agent Browser CLI?
Agent Browser CLI fits situations like: tasks that involve Browser automation.
How do I install Agent Browser CLI in Claude Code?
Run `npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a claude-code`. Or copy the skill folder (skills/agent-browser-cli in sleepinginsummer/agent-browser-cli) into .claude/skills/agent-browser-cli in your project. Claude Code loads it when a task matches its description.
How do I install Agent Browser CLI in Codex?
Run `npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a codex`. Or copy the skill folder (skills/agent-browser-cli in sleepinginsummer/agent-browser-cli) into .agents/skills/agent-browser-cli in your project. Codex loads it when a task matches its description.
Can I use Agent Browser CLI in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sleepinginsummer/agent-browser-cli --skill agent-browser-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-browser-cli, .gemini/skills/agent-browser-cli, .github/skills/agent-browser-cli and .opencode/skills/agent-browser-cli in your project.
What does Agent Browser CLI need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Browser CLI is instructions for the agent only.
Does Agent Browser CLI access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Browser CLI safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Browser CLI use?
Agent Browser CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Browser CLI use?
About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.
What are the alternatives to Agent Browser CLI?
Skills that share tags, products or a category with Agent Browser CLI: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dev-Browser CLI Automation (SawyerHood/dev-browser, 6.7k stars), Agent Browser (superagent-ai/grok-cli, 3.5k stars) and Browser Automation (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Browser CLI?
sleepinginsummer (a GitHub user) maintains it in sleepinginsummer/agent-browser-cli, which has 630 GitHub stars. The repository was last updated on August 2, 2026.
Source: sleepinginsummer/agent-browser-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.