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 agentmods add instructions/amos144/zerotoken/claude-mdgit 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/instructions/amos144/zerotoken/claude-md)<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>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 | $0.03036 | $0.03036 |
| Opus 5 | $0.01518 | $0.01518 |
| Sonnet 5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00304 | $0.00304 |
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.
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
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.
- 5d ago First seen · 351 lines · 3,036 tokens per session scan A c5056da12c49
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).