agentmods.dev

ai-browser-tester: Instructions file for Claude Code

CLAUDE.md

ai-browser-tester CLAUDE.md is an instructions file for Claude Code from Ryn-Mic/ai-browser-tester. It costs 2,125 tokens per session, scanned A, a copy of ai-browser-tester AGENTS.md, Apache-2.0.

Project instructions for building ai-browser-tester, an MCP-based browser automation testing tool. They describe its current TypeScript monorepo—a repository containing multiple related packages—and its browser-control architecture.

In plain words
What is it for?
Guiding development of browser snapshots, controlled actions, event handling, audit logs, browser extensions and MCP tool adapters.
Why use it?
They give a coding agent the project status, design rules and implementation direction needed to work consistently in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is Ryn-Mic/ai-browser-tester's own configuration. It tells Claude Code how to work on ai-browser-tester itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-browser-tester configures →

not rated 0repo 1mo ago A scan 2,125 tokens copy · 91% Apache-2.0
View source ↗ Ryn-Mic/ai-browser-tester
Reuse

Borrowing it

Nothing to install: this file belongs to Ryn-Mic/ai-browser-tester. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Ryn-Mic/ai-browser-tester/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Ryn-Mic/ai-browser-tester

Made for: Claude Code.

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 ai-browser-tester CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryn-mic/ai-browser-tester/claude-md.svg)](https://agentmods.dev/instructions/ryn-mic/ai-browser-tester/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ryn-mic/ai-browser-tester/claude-md"><img src="https://agentmods.dev/badge/instructions/ryn-mic/ai-browser-tester/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,125 This file is loaded in full into every session.
When invoked 2,125 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% copy Near-identical to another mod 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 5.1 $0.02125 $0.02125
Opus 5 $0.01063 $0.01063
Sonnet 5 $0.00425 $0.00425
Haiku 4.5 $0.00213 $0.00213

Measured 7d ago against content hash 16e203bd6291, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-browser-tester 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 7d 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.

Origin

This is a copy

91% identical to ai-browser-tester AGENTS.md — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

本文件为后续 Claude Code / AI agent 在本项目中工作的项目级说明。

项目概述

本项目目标是构建一个 MCP-first 浏览器控制工具，供 Codex、Claude Code 或任何兼容 MCP client 执行自动化测试：

  • 浏览器侧通过 Chrome/Edge 扩展或早期油猴脚本注入页面。
  • 页面侧把 DOM、可访问性信息、可交互元素和页面事件转换成 LLM 可消费的结构化快照。
  • MCP client 负责规划；本项目通过 MCP 暴露受控、可审计、ref-only 的浏览器能力。
  • 控制方式优先采用 snapshot -> ref -> action -> result -> snapshot -> assertion 的闭环。

主要计划文档在：

  • docs/ai-browser-tester-plan.md

当前项目状态

第一轮闭环（implementation-order Phase 1–7）已落地：

  • 已初始化 pnpm TypeScript monorepo。
  • packages/protocol：Zod 协议 schemas + 单元测试（JSON-RPC、握手、tab、snapshot、action、result、event、error、redaction、safety）。
  • packages/page-controller：与浏览器无关的 PageController（snapshot/act/getEvents、ref registry、action executor、event collector、snapshot redaction）。
  • apps/bridge：WebSocket handshake、pairing token 校验、协议版本协商、session manager、extension router、policy 层、audit log（JSONL + fill 值遮蔽）、严格 BrowserTools、以及与传输解耦的 MCP tool adapter（createMcpToolServer）。
  • apps/extension：MV3 manifest（host 权限仅 localhost/127.0.0.1，无 <all_urls>）、background service worker、pairing token WebSocket client、tab registry、page 请求路由、content script + PageController。dev-only automation hook 仅在 AI_BROWSER_TESTER_DEV=1 编译。
  • tests/：共享 e2e/harness.ts + 8 个 E2E 规格（login、form、todo/modal、open shadow DOM + same-origin iframe、SPA route change、blocked/stale-tab URL、high-risk 确认、内部滚动容器），真实加载 unpacked MV3 扩展跑通 snapshot -> ref -> action -> assert -> events，并校验 audit、密码遮蔽、无 evaluate、无 <all_urls>、policy fail-closed。
  • docs/：protocol.md、security.md、architecture.md、testing.md 已同步到实现现状。

当前优先项：

  • 2026-07-10 已完成 production unpacked Chrome + Codex stdio MCP 真实浏览器测试及阻断问题复测，证据见 docs/mcp-live-test-report-2026-07-10.md；用户随后已授权发布 @ryn-mic/ai-browser-tester npm MCP 以及包含独立 extension ZIP/SHA assets 的 GitHub Release，扩展签名和商店上架仍搁置。
  • Phase 12 snapshot quality/scale controls 已落地：可配置文本/元素上限、landmark 提取、ARIA widget 状态（checked/expanded/selected）、精确重复文本去重、列表/表格/dialog/内部滚动容器语义摘要、显式 truncation/去重元数据（page.truncated）、遮蔽先于输出/去重/裁剪，以及大页面/密钥密集回归测试。稳定 ref、事件/错误聚合摘要为有意后延项。
  • Phase 13 extension installation/permissions model 已落地：unpacked extension 构建包含 options page，README 提供 Chrome/Edge 安装与 pairing token/bridge URL 配置说明；manifest 永久 host permissions 仍仅 localhost/127.0.0.1，无 <all_urls>；非本地站点通过 options page 逐 origin 请求 optional host permission，并用动态 content script registration 注入 page agent。
  • Phase 14 observability/diagnostics 已落地：browser_diagnostics 只读工具、SessionManager.diagnostics() 会话/标签/策略健康摘要、BRIDGE_ERROR_CATALOG 全错误码目录、诊断 URL 遮蔽与 troubleshooting 文档。
  • Phase 15 agent regression/release readiness 已落地：pnpm test:agent scripted agent 回归、AgentScenarioRecorder 指标 JSON（成功率/工具调用数/耗时/snapshot 大小/错误分布）、pnpm release:gate 发布门禁、兼容矩阵与 release checklist。
  • CI（.github/workflows/release-gate.yml）在 PR 和 push 上运行 pnpm release:gate；pnpm smoke:mcp（scripts/claude-code-mcp-smoke.mjs）对真实 stdio MCP CLI 做 transport smoke（initialize/tools.list/tools.call diagnostics），见 docs/claude-code-mcp-smoke.md。
  • docs/next-phase-plan.md 中的 MCP readiness、手动扩展安装、Codex MCP 注册和真实浏览器测试已经完成；CI 打包已落地，HTTP、内置 real-model regression、扩展签名/商店发布仍后置。

Read the full file on GitHub · 134 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. 7d ago First seen · 134 lines · 2,125 tokens per session scan A 16e203bd6291

Subscribe to this mod's changes

ai-browser-tester CLAUDE.md is an instructions file published in the GitHub repository Ryn-Mic/ai-browser-tester (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,125 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to ai-browser-tester AGENTS.md, differing in 16 lines, and is treated as a copy.

Browser automationE2E testingTesting
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens