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 AMOS144/ZeroToken --skill zerotoken-openclawgit clone --depth 1 https://github.com/AMOS144/ZeroTokenWrote 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/amos144/zerotoken/zerotoken-openclaw)<a href="https://agentmods.dev/skills/amos144/zerotoken/zerotoken-openclaw"><img src="https://agentmods.dev/badge/skills/amos144/zerotoken/zerotoken-openclaw/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/amos144/zerotoken/zerotoken-openclaw"><img src="https://agentmods.dev/badge/skills/amos144/zerotoken/zerotoken-openclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.04882 |
| Opus 5 | $0.00018 | $0.02441 |
| Sonnet 5 | $0.00007 | $0.00976 |
| Haiku 4.5 | $0.00004 | $0.00488 |
Grade A, and why
zerotoken-openclaw 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 9d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZeroToken 浏览器自动化(OpenClaw)
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
何时使用 / 何时不该用
- 适合使用:
- 需要通过 OpenClaw + ZeroToken MCP 做浏览器自动化,并且未来会 重复 / 定时执行 的任务。
- 已经有一次完整的浏览器操作轨迹,希望将其 转成低 Token 消耗的脚本 来复用。
- 不适合使用:
- 只想临时操作一次、没有复用需求的场景(直接用 ZeroToken MCP 即可)。
- 页面强依赖人工决策,大量步骤都需要
fuzzy_point介入、无人值守难以兜底的任务。
前置条件
- 当前环境中已能通过 MCP 访问名为
zerotoken的服务器(或等价的 MCP server id)。 - 执行浏览器操作前需先调用
browser_init;完成后可选调用browser_close。
OpenClaw 使用前准备(HTTP 模式)
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:
- 手动启动 HTTP 服务(在后台常驻):
zerotoken-mcp-http,或zerotoken-mcp --transport streamable-http- 默认端口 8000,可用
--port或环境变量ZEROTOKEN_HTTP_PORT覆盖。
- OpenClaw 配置:在
openclaw.json的mcpServers.zerotoken中,使用 URL 而非 command:
具体字段名以 OpenClaw 文档为准(可能为{ "mcpServers": { "zerotoken": { "url": "http://localhost:8000/mcp" } } }streamable-http或url)。
MCP 未配置 / 未安装 ZeroToken 时的处理
当调用 ZeroToken 相关 MCP 工具失败,并出现类似以下症状时:
- 找不到名为
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:
- 明确告知用户:ZeroToken MCP 尚未在当前环境安装或启用,暂时无法使用浏览器自动化脚本能力。
- 询问用户当前所用平台(如「Cursor / OpenClaw / 其他支持 MCP 的客户端」),并指导用户安装 ZeroToken 及浏览器依赖:
- OpenClaw + MCPorter:
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」)。 - 如果平台有 MCP Marketplace / 插件市场:
提示用户在市场中搜索并启用zerotokenMCP。 - 如果是本地 Python 环境(如命令行 / 开发机):
提示用户依次执行:- 安装包:
pip install zerotoken - 安装 Playwright 浏览器依赖(否则浏览器工具会报错):
- 普通环境:
playwright install chromium - 如使用 uv:
uv run playwright install chromium --with-deps
- 普通环境:
- 启动 MCP Server:OpenClaw 在后台运行
zerotoken-mcp-http;Cursor 等 IDE 运行zerotoken-mcp(或由客户端自动拉起)。 - 在客户端中,将该 MCP server 注册为 id 为
zerotoken的 MCP;OpenClaw 需在openclaw.json中配置 URL(见「OpenClaw 使用前准备」)。
- 安装包:
- OpenClaw + MCPorter:
- 在用户确认 ZeroToken 已安装并启用后,Agent 再次从
browser_init开始执行 ZeroToken 相关步骤。
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.
- 9d ago First seen · 259 lines · 36 tokens per session scan A 6ba98ad44e4c
zerotoken-openclaw is a skill published in the GitHub repository AMOS144/ZeroToken (454 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 4,882 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 2026-08-30.
Other skills, from other repositories
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.
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
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.
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.
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…