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 5.5 | $0.00014 | $0.01953 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 259 lines · 36 tokens per session scan A 6ba98ad44e4c
zerotoken-openclaw is a skill published in the GitHub repository AMOS144/ZeroToken (452 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 4,882 once invoked, about $0.0001 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 2026-08-30.
zerotoken-openclaw compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zerotoken-openclawAMOS144/ZeroToken | Skill | 452 | 6mo ago | MIT | A | 36 | 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 |