ZeroToken CLAUDE.md

ZeroToken CLAUDE.md is an instructions file for coding agents from AMOS144/ZeroToken. It costs 3,036 tokens per session, scanned A, original, MIT.

Project instructions for ZeroToken, a browser-automation engine for AI agents. They describe how browser actions return detailed records, how those actions are saved as a trajectory, and how the trajectory becomes an AI-readable prompt.

In plain words
What is it for?
Working on browser actions such as opening pages, clicking, entering text, reading content, and extracting structured data, as well as recording and exporting those actions.
Why use it?
They give coding agents the project structure and the intended flow of browser operations. This reduces confusion when changing the browser controller, operation history, or prompt-export logic.

Instructions file

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.

agentmods
npx agentmods add instructions/amos144/zerotoken/claude-md
Clone the repo
git clone --depth 1 https://github.com/AMOS144/ZeroToken

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.

agentmods badge for ZeroToken CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amos144/zerotoken/claude-md.svg)](https://agentmods.dev/instructions/amos144/zerotoken/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amos144/zerotoken/claude-md"><img src="https://agentmods.dev/badge/instructions/amos144/zerotoken/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,036 This file is loaded in full into every session.
When invoked 3,036 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03036 $0.03036
Opus 5 $0.01518 $0.01518
Sonnet 5 $0.00607 $0.00607
Haiku 4.5 $0.00304 $0.00304

Measured 5d ago against content hash c5056da12c49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ZeroToken CLAUDE.md 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 5d 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.

CLAUDE.md · 351 lines

How it starts

The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZeroToken 项目开发指南

项目概述

ZeroToken 是一个面向 AI Agent 的浏览器自动化 MCP 引擎,核心目标是:

  • 降低 Token 消耗 - 通过轨迹记录与 AI 提示导出,供 Skills 等模块分析
  • 详细执行上下文 - 每次操作记录完整状态、截图、模糊点
  • 模糊点标记 - 显式标记需 AI/人判断的步骤

核心架构

设计思路

AI Agent (ReAct 模式)
       ↓
   MCP 工具调用 (原子能力)
       ↓
   返回结构化 OperationRecord (含 fuzzy_point)
       ↓
   记录完整 Trajectory
       ↓
   trajectory.to_ai_prompt_format() 导出含模糊点的 AI 提示
       ↓
   Skills 或外部模块进一步处理

模块职责

1. BrowserController (controller.py)
  • 职责: 浏览器控制,返回详细的 OperationRecord
  • 关键特性:
    • 全局单例模式
    • 每个操作返回完整上下文(页面状态、截图、结果)
    • 自动等待机制
    • 操作历史追踪
# 核心方法
- open(url) → OperationRecord
- click(selector) → OperationRecord
- input(selector, text) → OperationRecord
- get_text(selector) → OperationRecord
- extract_data(schema) → OperationRecord  # AI 节点能力
2. TrajectoryRecorder (trajectory.py)
  • 职责: 记录完整的操作轨迹,导出 AI 提示
  • 关键特性:
    • 绑定 BrowserController 自动记录
    • 导出 AI 友好的提示格式(含模糊点 [需判断: {reason}]
    • 轨迹持久化存储
# 核心方法
- start_trajectory(task_id, goal)
- record_operation(record)
- complete_trajectory() → Trajectory
- trajectory.to_ai_prompt_format() → str  # AI 提示格式

数据结构

OperationRecord

{
    "step": int,
    "action": str,
    "params": dict,
    "result": {
        "success": bool,
        "navigated": bool,  # click 专属
        "value": any,  # extract 专属
        ...
    },
    "page_state": {
        "url": str,
        "title": str,
        "timestamp": str
    },
    "screenshot": str,  # base64
    "error": str,
    "fuzzy_point": {  # 可选,需 AI/人判断时存在
        "requires_judgment": bool,
        "reason": str,
        "hint": str
    },
    "timestamp": str
}

Trajectory

{
    "task_id": str,
    "goal": str,
    "start_time": str,
    "end_time": str,
    "operations": List[OperationRecord],
    "metadata": {
        "total_steps": int,
        "successful_steps": int,
        "failed_steps": int
    }
}

开发规范

代码风格

  • 使用 async/await 异步编程
  • 所有浏览器操作必须等待元素就绪
  • 错误处理要返回统一的响应格式
  • 操作记录必须包含完整上下文

Read the full file on GitHub · 351 lines

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.

  1. 5d ago First seen · 351 lines · 3,036 tokens per session scan A c5056da12c49

Subscribe to this mod's changes

ZeroToken CLAUDE.md is an instructions file published in the GitHub repository AMOS144/ZeroToken (454 stars, last pushed 4mo ago), licensed MIT. It adds 3,036 tokens to every session, about $0.0152 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.