Oya Browser
OyadotAI/oya-browser
Drive real Chrome browsers through Oya Browser. An agent skill from OyadotAI/oya-browser.
A skill your agent uses when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.
$ npx skills add AMOS144/ZeroToken --skill zerotoken-openclaw -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AMOS144/ZeroToken zerotoken-openclaw --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/AMOS144/ZeroToken.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/zerotoken-openclaw .claude/skills/zerotoken-openclaw && 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 "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .claude/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclawType 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 AMOS144/ZeroToken --skill zerotoken-openclaw -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AMOS144/ZeroToken zerotoken-openclaw --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMOS144/ZeroToken.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/zerotoken-openclaw .agents/skills/zerotoken-openclaw && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .agents/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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 AMOS144/ZeroToken --skill zerotoken-openclaw -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AMOS144/ZeroToken zerotoken-openclaw --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMOS144/ZeroToken.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/zerotoken-openclaw .cursor/skills/zerotoken-openclaw && 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 "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .cursor/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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/AMOS144/ZeroToken.git --path skills/zerotoken-openclaw--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 AMOS144/ZeroToken --skill zerotoken-openclaw -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AMOS144/ZeroToken zerotoken-openclaw --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMOS144/ZeroToken.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/zerotoken-openclaw .gemini/skills/zerotoken-openclaw && 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 "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .gemini/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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 AMOS144/ZeroToken zerotoken-openclawInstalls 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 AMOS144/ZeroToken --skill zerotoken-openclaw -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AMOS144/ZeroToken.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/zerotoken-openclaw .github/skills/zerotoken-openclaw && 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 "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .github/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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 AMOS144/ZeroToken --skill zerotoken-openclaw -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AMOS144/ZeroToken zerotoken-openclaw --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMOS144/ZeroToken.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/zerotoken-openclaw .opencode/skills/zerotoken-openclaw && 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 "zerotoken-openclaw" agent skill from https://github.com/AMOS144/ZeroToken/tree/main/skills/zerotoken-openclaw into .opencode/skills/zerotoken-openclaw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zerotoken-openclaw", 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.
zerotoken-openclawA skill your agent uses when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.
Zerotoken Openclaw is an agent skill from AMOS144/ZeroToken. Use when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation, covering Browser automation and MCP servers. It works with Model Context Protocol and Playwright. The repository describes itself as: ZeroToken — Record once, automate forever. A lightweight MCP for agent-driven browser automation, script recording, and scheduled execution. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e6cc92c. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
pipplaywrightuvFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip and uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Zerotoken Openclaw loads about 2.9k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 780 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.
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.
The full file from AMOS144/ZeroToken at commit e6cc92c, republished under its MIT licence (© AMOS144). 780 words, ~2,894 tokens.
.claude/skills/zerotoken-openclaw/SKILL.md (or your agent's skills folder).教会 Agent 使用 ZeroToken MCP 做浏览器自动化、轨迹录制与脚本重放。旨在让 OpenClaw 执行定时/重复任务时尽量少消耗 Token。
ZeroToken 项目主页:https://github.com/AMOS144/zerotoken
fuzzy_point 介入、无人值守难以兜底的任务。zerotoken 的服务器(或等价的 MCP server id)。browser_init;完成后可选调用 browser_close。当通过 OpenClaw / MCPorter 使用 ZeroToken 时,因其每次调用会新建进程,导致 browser 状态丢失。需改用 Streamable HTTP 传输模式,服务常驻:
zerotoken-mcp-http,或zerotoken-mcp --transport streamable-http--port 或环境变量 ZEROTOKEN_HTTP_PORT 覆盖。openclaw.json 的 mcpServers.zerotoken 中,使用 URL 而非 command:{
"mcpServers": {
"zerotoken": {
"url": "http://localhost:8000/mcp"
}
}
}streamable-http 或 url)。当调用 ZeroToken 相关 MCP 工具失败,并出现类似以下症状时:
zerotoken 的 MCP server;browser_init / trajectory_start 等工具报「tool not found」「MCP server unavailable」或 import 相关错误;Agent 应按以下顺序处理:
mcporter install zerotoken --target openclaw --configure。重要:OpenClaw 需用 HTTP 模式,先在后台运行 zerotoken-mcp-http,再在 openclaw.json 中将 mcpServers.zerotoken 配置为 {"url": "http://localhost:8000/mcp"}(见上文「OpenClaw 使用前准备」)。zerotoken MCP。pip install zerotokenplaywright install chromiumuv run playwright install chromium --with-depszerotoken-mcp-http;Cursor 等 IDE 运行 zerotoken-mcp(或由客户端自动拉起)。zerotoken 的 MCP;OpenClaw 需在 openclaw.json 中配置 URL(见「OpenClaw 使用前准备」)。browser_init 开始执行 ZeroToken 相关步骤。browser_init(可选 stealth: true 反爬)、browser_close、browser_open、browser_click、browser_input、browser_get_text、browser_get_html、browser_screenshot、browser_wait_for、browser_extract_datatrajectory_start、trajectory_complete、trajectory_get、trajectory_list、trajectory_load、trajectory_delete、trajectory_to_script(轨迹转脚本并保存到数据库)script_save、script_list、script_load、script_deleterun_script:无 LLM 回放脚本执行 { "task_id": "...", "vars"?: {...} }{ "session_id": "...", "resolution": {...} }(由上层编排器在 DFU/模糊点暂停后恢复)run_script_by_job_id:定时任务一步执行,{ "binding_key": "job_id", "vars"?: {...} },内部查绑定并执行session_list、session_get(session_id):查询录制 / 回放会话明细,用于 debug、审计、定时任务复盘脚本、轨迹与会话均由 MCP 后端存储在 SQLite 数据库 中,通过上述工具访问,不依赖本地文件路径。
可选参数:include_screenshot: false 减少响应体积;auto_save: true / adaptive: true 用于自适应元素定位。
| 工具 / action | 典型用途 |
|---|---|
| browser_init | 初始化浏览器会话(可选 headless/stealth) |
| browser_open | 打开登录页或任意目标页面 |
| browser_click | 点击按钮、链接、tab 等 |
| browser_input | 在输入框内输入用户名、密码、搜索关键字等 |
| browser_get_text/get_html | 读取文本或整段 HTML,用于后续解析 |
| browser_wait_for | 等待某段文本出现/消失,避免页面还没加载完 |
| browser_screenshot | 截图留档或调试 |
| browser_extract_data | 从列表 / 表格中抽数据 |
| trajectory_start/complete | 录制一次完整的浏览器操作轨迹 |
trajectory_start(task_id, goal) → browser_init → browser_open / browser_click / browser_input 等 → trajectory_complete(export_for_ai: true)trajectory_list 查 task_id → trajectory_load(task_id, format) 获取轨迹trajectory_delete(task_id) 删除;browser 工具可传 include_screenshot: falsesuccess: false、code、retryable,可按 retryable 决定是否重试仅在以下情况根据轨迹生成可复用脚本(避免徒增 Token):
不主动生成:未提复用、未提定时/重复时,只做轨迹录制与保存。若用户后续要脚本再生成。
当 OpenClaw 以定时任务触发本 Skill 时,事件参数中会携带该任务的 job_id。ZeroToken 使用 job_id 作为绑定键(binding_key),并在 MCP 数据库的 script_bindings 表中维护「job_id ↔ 脚本」关系。
Agent 必须遵守以下约定:
run_script_by_job_id(binding_key=job_id, vars?) 一步执行:MCP 内部查绑定、合并 default_vars、执行脚本。script_binding_get(binding_key=job_id),再 run_script(task_id, vars=merged_vars)。run_script_by_job_id 或 script_binding_get(job_id) 返回「未找到」:job_id 或未标记为定时任务的场景:browser_* + trajectory_* 完成当前需求,不主动查找/执行脚本。开发者应在 ZeroToken 侧或 OpenClaw 的集成层中,使用 script_binding_set(binding_key=job_id, script_task_id=..., default_vars?, description?) 预先将定时任务 job_id 与脚本 task_id 明确绑定。本 Skill 仅通过 job_id 查询绑定,不对映射关系做额外推断。
当 Agent 收到带 job_id 的定时任务配置请求(如用户说「设为每日执行」「把这个任务设为定时」),且 OpenClaw 已传入 job_id 时,必须完成以下端到端流程:
trajectory_list 取最新)。trajectory_load(task_id) 检查轨迹是否存在;若无则提示用户先录制。script_load(task_id) 检查脚本是否存在;若无则调用 trajectory_to_script(task_id, stealth?) 根据轨迹生成并保存。script_binding_set(binding_key=job_id, script_task_id=task_id, default_vars?, description?) 将 job_id 与脚本绑定。重要:task_id 贯穿 trajectory → script → binding,三者必须一致。录制时用的 task_id 即脚本的 task_id,也是 binding 的 script_task_id。
若 script_binding_set 返回 SCRIPT_NOT_FOUND,说明脚本不存在,应先 trajectory_to_script(task_id) 再绑定。
若目标站点(如 B 站、小红书等)易被检测为自动化并拦截,需:
browser_init 传 stealth: true,降低被识别概率。trajectory_to_script(task_id, stealth=true) 使生成的脚本中 browser_init 包含 stealth: true。run_script 会按脚本中的 browser_init 参数执行,若脚本含 stealth: true 则自动启用反检测。stealth 模式会启用:启动参数伪装、navigator 指纹伪装、Sec-CH-UA 头、WebGL 指纹伪装等。
hint 字段,可按提示执行 trajectory_to_script(script_task_id) 重新生成脚本(轨迹仍在时),再重试 run_script_by_job_id。脚本通过 script_save / script_load 读写,结构示例:
{
"task_id": "login_daily",
"goal": "每日登录并拉取报表",
"steps": [
{ "action": "browser_init", "params": { "headless": true, "stealth": true } },
{ "action": "trajectory_start", "params": { "task_id": "login_daily", "goal": "每日登录并拉取报表" } },
{ "action": "browser_open", "params": { "url": "https://example.com/login" } },
{ "action": "browser_input", "params": { "selector": "#user", "text": "{{username}}" } },
{ "action": "browser_click", "params": { "selector": "#submit" },
"fuzzy_point": { "reason": "验证码需识别", "hint": "可调 browser_extract_data 或等待人工输入" } },
{ "action": "browser_get_text", "params": { "selector": ".report" } }
]
}steps:有序数组;每步 action 对应 MCP 工具名,params 为该工具入参。fuzzy_point:记录该步「需要 AI/人介入」的语义信息(reason、hint),本身不会让 ScriptEngine 自动暂停;只有当为该步配置了匹配的 DFU / 执行点时,run_script 执行到该步才会返回 status="paused"。params 中可用 {{varname}},执行前由 Agent 或配置替换(如环境变量、用户输入),或在 ExecutionPoint/DFU 暂停时由上层生成 resolution.vars 合并进运行时变量环境。含 {{varname}} 的脚本,执行前必须提供对应 vars(run_script 的 vars 或 run_script_by_job_id 的 vars/binding 的 default_vars),否则占位符会保留字面量,可能导致无效输入。只有在以下两种情况下,才去查找并执行脚本:
在这些情况下:
script_load(task_id) 从 MCP 数据库读取脚本;若无则调用 trajectory_to_script(task_id) 根据轨迹生成并保存(否则不要擅自造脚本)。run_script(task_id, vars?) 由 MCP 内的 ScriptEngine 自动按 steps 顺序执行脚本,无需 LLM,执行过程写入 session;返回形如 {"success": ..., "status": "success|paused|failed", "session_id": ...}。status="paused"(例如命中 DFU / 执行点 / 失败重试上限):pause_event(包含 step_index、dfu_id、提示文案与需要生成的 vars),做一次决策或生成 vars;run_script(session_id=..., resolution={...}) 恢复执行,由 ScriptEngine 继续顺序执行后续 steps。非定时/一次性任务:优先只用 browser_ + trajectory_ 录制与完成当前任务,不主动查找/执行脚本。**
脚本是「数据驱动的 MCP 调用序列」,存于 MCP 数据库,由 ScriptEngine 自动化回放,Token 消耗低且可通过 session 追踪每次执行。
fuzzy_point 的 OperationRecord / 步骤时,可把 reason、hint 视作提示,根据当前页面决定是否额外调用 browser_extract_data、browser_input 等,再继续。run_script(ScriptEngine 自动回放)时:是否暂停由 DFU/执行点规则决定(dfu_* 配置 + trigger 匹配),而不是单靠 fuzzy_point。若某步既有 fuzzy_point 又命中 DFU,则 ScriptEngine 会在该步返回 status="paused" + pause_event,由上层 Agent 决定 resolution 后再恢复。run_script 模式下会直接按脚本跑完,可能需要通过 session 结果+日志事后审计。推荐:直接调用 trajectory_to_script(task_id, script_task_id?, prepend_init?, stealth?),MCP 会从数据库加载轨迹、转换为脚本并保存,返回 task_id。若目标站点易被反爬拦截,传 stealth=true 使生成的脚本中 browser_init 包含 stealth: true。
若需手动控制,可参考以下流程:
输入:trajectory_load(task_id, format="json") 或 format="ai_prompt";必要时先用 trajectory_list 选 task_id。
action 映射:轨迹中的 operations[].action 为内部名,生成脚本时必须映射为 MCP 工具名;执行时按 MCP 工具名调用。
| 轨迹 action | 脚本/MCP action |
|---|---|
| open | browser_open |
| click | browser_click |
| input | browser_input |
| get_text | browser_get_text |
| get_html | browser_get_html |
| screenshot | browser_screenshot |
| wait_for | browser_wait_for |
| extract_data | browser_extract_data |
轨迹不包含 browser_init、trajectory_start;生成脚本时在 steps 开头补上这两步(若需录制回放)。
输出:调用 script_save(task_id, goal, steps) 写入 MCP 数据库;steps 中 action 用映射后的 MCP 名,params 与轨迹一致,selector_candidates、fuzzy_point 从轨迹带出。
trajectory_list 或 script_list 得到 task_id,用 script_load(task_id) 取脚本;若无则提示「该任务尚无脚本,是否根据轨迹生成?」并直接调用 trajectory_to_script(task_id) 生成并保存。run_script 或录制产生 session,用 session_list、session_get(session_id) 查看。将本 Skill 放入 OpenClaw 的 skills 目录之一:
./skills/zerotoken-openclaw/(仅当前项目)~/.openclaw/skills/zerotoken-openclaw/clawhub install zerotoken-openclaw(若已发布)从本仓库安装示例:克隆后复制 skills/zerotoken-openclaw/ 到上述路径之一。
zerotoken-mcp-http 或 openclaw.json 仍用 command 而非 url,导致每次调用新建进程、browser 状态丢失。browser_init 就直接使用 browser_open / browser_click,导致第一次调用失败或异常。export_for_ai: true,后续生成脚本时需要额外处理轨迹数据。task_id 在 trajectory 与 script 中不一致,导致 script_load(task_id) 找不到对应脚本。fuzzy_point 的脚本,容易在模糊点步骤卡住;这类任务应提前评估是否需要人工兜底。© AMOS144, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/zerotoken-openclaw of AMOS144/ZeroToken.
Open the folder on GitHubat commit e6cc92c
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in AMOS144/ZeroToken, which our catalogue first saw on October 7, 2026.
Zerotoken Openclaw 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 |
|---|---|---|---|---|---|---|
| Zerotoken Openclaw this skillAMOS144/ZeroToken | 455 | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Oya BrowserOyadotAI/oya-browser | 349 | — | ~2.1k | Automated safety check: Pass | Custom licence | |
| Skillredf0x1/camofox-mcp | 117 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Browser MCP Agentantibrow/anti-detect-browser-skills | 17 | 1 repos | ~4.2k | Automated safety check: Warn | MIT | |
| Browser UseQwenLM/qwen-code-examples | 143 | — | ~451 | Automated safety check: Pass | None | |
| Cloudflare Browser Renderingeinverne/dotfiles | 121 | — | ~4.9k | Automated safety check: Pass | GPL-3.0 |
OyadotAI/oya-browser
Drive real Chrome browsers through Oya Browser. An agent skill from OyadotAI/oya-browser.
redf0x1/camofox-mcp
Anti-detection browser automation MCP skill for OpenClaw agents with 47 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.
antibrow/anti-detect-browser-skills
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…
QwenLM/qwen-code-examples
Control browser pages using the Playwright MCP server. An agent skill from QwenLM/qwen-code-examples.
einverne/dotfiles
Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing.
feder-cr/invisible_playwright_mcp
What the invisible_playwright_mcp browser server needs on this machine - the patched Firefox it drives, which the server downloads on its own the first time…
Works with
Categories
A skill your agent uses when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks. Zerotoken Openclaw is an agent skill from AMOS144/ZeroToken. Use when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.
Zerotoken Openclaw fits situations like: using ZeroToken MCP via OpenClaw for browser automation; trajectory recording and low-token replay; especially for recurring; scheduled browser tasks.
Run `npx skills add AMOS144/ZeroToken --skill zerotoken-openclaw -a claude-code`. Or copy the skill folder (skills/zerotoken-openclaw in AMOS144/ZeroToken) into .claude/skills/zerotoken-openclaw in your project. Claude Code loads it when a task matches its description.
Run `npx skills add AMOS144/ZeroToken --skill zerotoken-openclaw -a codex`. Or copy the skill folder (skills/zerotoken-openclaw in AMOS144/ZeroToken) into .agents/skills/zerotoken-openclaw in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AMOS144/ZeroToken --skill zerotoken-openclaw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zerotoken-openclaw, .gemini/skills/zerotoken-openclaw, .github/skills/zerotoken-openclaw and .opencode/skills/zerotoken-openclaw in your project.
Going by SKILL.md and its folder, Zerotoken Openclaw needs the command-line tools its instructions call (pip, playwright and uv). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use pip and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Zerotoken Openclaw is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Zerotoken Openclaw: Oya Browser (OyadotAI/oya-browser, 349 stars), Skill (redf0x1/camofox-mcp, 117 stars), Browser MCP Agent (antibrow/anti-detect-browser-skills, 17 stars) and Browser Use (QwenLM/qwen-code-examples, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
AMOS144 (a GitHub user) maintains it in AMOS144/ZeroToken, which has 455 GitHub stars. The repository was last updated on May 8, 2026.
Source: AMOS144/ZeroToken on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.