Borrowing it
Nothing to install: this file belongs to insung8150/AgentWebSearch-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/insung8150/AgentWebSearch-MCP/master/CLAUDE.mdgit clone --depth 1 https://github.com/insung8150/AgentWebSearch-MCPWrote 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/insung8150/agentwebsearch-mcp/claude-md)<a href="https://agentmods.dev/instructions/insung8150/agentwebsearch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/insung8150/agentwebsearch-mcp/claude-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.
<a href="https://agentmods.dev/instructions/insung8150/agentwebsearch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/insung8150/agentwebsearch-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01300 | $0.01300 |
| Opus 5 | $0.00650 | $0.00650 |
| Sonnet 5 | $0.00260 | $0.00260 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
AgentWebSearch-MCP 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
AgentWebSearch-MCP is an API-key-free local web search system using Chrome DevTools Protocol (CDP) for parallel web searches. Includes MCP server for Claude Code integration.
Optional Model: AgentCPM-Explore - A 4B model from OpenBMB/THUNLP specifically trained for search agent tasks. Required only for the agentcpm tool.
Commands
Start Chrome instances (required before search)
python chrome_launcher.py start # Start 3 Chrome instances (ports 9222-9224)
python chrome_launcher.py status # Check status
python chrome_launcher.py stop # Stop all
Run MCP server
python mcp_server.py # stdio mode (Claude Code)
python mcp_server.py --sse --port 8902 # SSE mode (HTTP)
Use MCP tools (recommended)
When running as MCP server, use the MCP tools directly:
web_search- Simple search (no LLM required)smart_search- Search + fetch URLs (no LLM required) ← Use this for most casesagentcpm- Agentic search using AgentCPM-Explore via SGLang
Do NOT run search_agent.py directly when using MCP. Just call the MCP tools.
Run standalone search agent (CLI only)
# Only for command line usage, not within Claude Code
python search_agent.py "query" --depth deep
python search_agent.py -i # Interactive mode
python search_agent.py --llm ollama "query" # CLI supports multiple backends
Architecture
mcp_server.py MCP server (4 tools)
|
+-- web_search → CDP search only
+-- fetch_urls → URL content fetch
+-- smart_search → Search + fetch (depth control)
+-- agentcpm → SGLang + AgentCPM-Explore + search + fetch
|
search_agent.py Standalone agent (CLI, supports multiple backends)
|
llm_adapters/ Unified LLM interface (for CLI)
|
cdp_search.py CDP-based parallel portal search
|
chrome_launcher.py Chrome instance lifecycle (ports 9222-9224)
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.
- 9d ago First seen · 146 lines · 1,300 tokens per session scan A c8b98720b34d
AgentWebSearch-MCP CLAUDE.md is an instructions file published in the GitHub repository insung8150/AgentWebSearch-MCP (20 stars, last pushed 6mo ago), licensed MIT. It adds 1,300 tokens to every session, about $0.0065 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.