What is mcp-browser-analyzer AGENTS.md?

A project instruction document for a browser-analysis application, giving an AI coding agent an overview of the codebase, its structure, features, and common commands. The project is a pnpm monorepo, meaning one repository contains multiple related packages managed together.

It is for orienting agents working on the browser extension and its Node.js server, including their directories and development commands.

It gives an agent project-specific context before it changes code, reducing the need to rediscover how the repository is organised.

How Maxkim321/mcp-browser-analyzer configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Maxkim321/mcp-browser-analyzer. 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/Maxkim321/mcp-browser-analyzer/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Maxkim321/mcp-browser-analyzer

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/maxkim321/mcp-browser-analyzer/agents-md/github.svg)](https://agentmods.dev/instructions/maxkim321/mcp-browser-analyzer/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/maxkim321/mcp-browser-analyzer/agents-md"><img src="https://agentmods.dev/badge/instructions/maxkim321/mcp-browser-analyzer/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/maxkim321/mcp-browser-analyzer/agents-md"><img src="https://agentmods.dev/badge/instructions/maxkim321/mcp-browser-analyzer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,960 This file is loaded in full into every session.

When invoked 2,960 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.02960	$0.02960
Opus 5.5	$0.01184	$0.01184
Sonnet 5.5	$0.00592	$0.00592
Haiku 4.5	$0.00296	$0.00296

Measured 1mo ago against content hash c81362fdcbae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-browser-analyzer AGENTS.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 1mo 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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — mcp-browser-analyzer 项目交接文档（给 AI 代理的项目入口）

本文件是 AI 代理（ZCode/Cursor/Trae/Codex 等）进入本项目的统一上下文。改代码前先读完。最后更新：2026-09-27（P8 混合检索 + P9 MCP 真接入交付后）。

1. 项目定位

独立开源的浏览器 AI Agent 插件：Vue3 MV3 扩展 + Node.js 服务端。支持总结/划词问答/深度研究/性能审计/跨页面记忆/外部工具接入（MCP）。差异化不在"又一个总结插件"，而在 Agent 可靠性工程（三层编排、分级 HITL、事件溯源、上下文压缩、注入防护、成本台账）+ MCP 宿主治理。

2. 仓库结构（pnpm monorepo）

mcp-browser-analyzer/
├── chrome-extension/          # MV3 扩展（Vue3 + vite）
│   ├── src/ui/sidepanel/      # 侧边栏主 UI（SidePanel.vue：聊天/审批卡/引用标签/用量条）
│   ├── src/background/        # service worker（消息路由；注意：WS 连接由侧边栏持有，不由 SW）
│   ├── src/content-script/    # Readability 正文提取 + 划词工具条（Shadow DOM closed）
│   └── extension/             # ⚠️ 构建产物+manifest（vite 插件生成）——这是 --load-extension 的加载根目录
├── agent-server/              # Node.js 服务端（CommonJS，端口 9999，WS+Dashboard 同端口）
│   ├── src/core/              # agent.js(ReAct循环) workflow.js(研究状态机) context-manager(压缩)
│   │                          # approval.js(分级审批) event-log.js(事件溯源+seq) injection-guard.js(注入防护)
│   │                          # llm.js+llm-providers.js(分级路由+Provider适配) usage-*(成本台账) trace-log.js
│   ├── src/tools/             # index.js(15个内置工具+registerDynamicTool) handler.js(分发)
│   │                          # mcp-registry.js(MCP纳管三道闸) lighthouse.js
│   ├── src/memory/            # store.js(卡片JSONL) retrieve.js(BM25) embedder.js(两级Embedder)
│   │                          # vector-store.js(向量JSONL+cardKey) rrf.js(RRF融合) hybrid.js(编排4模式)
│   │                          # embed-sync.js(回填CLI) wire.js(读写接线，recallForPrompt 为 async)
│   ├── src/mcp/client.js      # MCP Client（stdio+JSON-RPC 2.0，两代规范兼容）
│   ├── src/communication/     # ws-server.js（WS 消息主循环）
│   ├── eval/                  # run-eval.js(黄金评测) run-memory-ab.js(记忆A/B) run-hybrid-ab.js(三路对照)
│   │                          # fixtures/ results/（所有数字必须来自 results/ 真实产物）
│   ├── test/                  # node:test 单测 158 个（零网络；LLM/工具走 mock/override）
│   ├── mcp-demo.js / mcp-e2e.js / mcp-e2e 全真验证脚本（见 §5）
├── ai-code-review/            # 零依赖 AI 代码审查 CLI（github/gitlab/mock adapters）
└── docs/                      # PRD/TECHNICAL/RETROSPECT 等早期文档

Read the full file on GitHub · 96 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.

1mo ago First seen · 96 lines · 2,960 tokens per session scan A c81362fdcbae

Subscribe to this mod's changes

mcp-browser-analyzer AGENTS.md is an instructions file published in the GitHub repository Maxkim321/mcp-browser-analyzer (22 stars, last pushed 15d ago), licensed MIT. It adds 2,960 tokens to every session, about $0.0118 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 2026-09-28.

Writing and docs

mcp-browser-analyzer AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-browser-analyzer AGENTS.mdMaxkim321/mcp-browser-analyzer	Instructions file	22	15d ago	MIT	A	2,960	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

mcp-browser-analyzer: Instructions file for Codex