What is SearChat CLAUDE.md?

Project instructions for SearChat, a conversation-based search application with a Node.js backend and Vue frontend. The project is a monorepo, meaning one repository contains several related applications and shared tooling.

Use them when developing, running, or building the search server and web interface. They also provide context for the app's language-model, search-engine, and deep-research integrations.

They explain where the backend and frontend live, which technologies they use, and which commands run or build both parts. This helps an agent navigate the repository correctly.

How yokingma/SearChat configures Claude Code

About the project

SearChat is an AI conversational search engine that combines chat with results from multiple search providers and language-model services. It is intended for users who want multi-turn searching, model-assisted research, and generated reports. The catalogue instruction supports workflows for using or extending SearChat.

yokingma/SearChat · 1,062 stars · on GitHub · isou.chat

Reuse

Borrowing it

Nothing to install: this file belongs to yokingma/SearChat. 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/yokingma/SearChat/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yokingma/SearChat

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yokingma/searchat/claude-md/github.svg)](https://agentmods.dev/instructions/yokingma/searchat/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/yokingma/searchat/claude-md"><img src="https://agentmods.dev/badge/instructions/yokingma/searchat/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yokingma/searchat/claude-md"><img src="https://agentmods.dev/badge/instructions/yokingma/searchat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 852 This file is loaded in full into every session.

When invoked 852 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	$0.00852	$0.00852
Opus 5.5	$0.00341	$0.00341
Sonnet 5.5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash cbb94eba5ad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SearChat 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 2mo 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 · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 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

This is "Open AI Search" - a conversation-based search application with LLM support that includes Deep Research capabilities. It's built as a monorepo using Turborepo with two main applications: a Node.js/Koa backend server and a Vue.js frontend.

Architecture

Monorepo Structure

Root: Turborepo workspace with [email protected] package manager
apps/server: Node.js backend (Koa.js framework, TypeScript)
apps/web: Vue.js frontend (Vue 3, TypeScript, Vite, TDesign UI)

Key Technologies

Backend: Koa.js, TypeScript, LangChain, multiple LLM providers (OpenAI, Google, DeepSeek, etc.)
Frontend: Vue 3, TypeScript, Vite, Pinia (state management), TDesign Vue Next, Tailwind CSS
Build System: Turborepo for monorepo management
Search Engines: SearXNG, Bing, Google, Tavily integration
AI Features: Deep Research mode with iterative search and analysis

Development Commands

Root Level (Turborepo)

# Start development servers for both apps
turbo dev
# or
yarn dev

# Build all applications
turbo build
# or
yarn build

Server (apps/server)

# Development with hot reload
yarn dev

# Production start
yarn start

# Type checking
yarn check-types

# Build TypeScript
yarn build

Web (apps/web)

# Development server
yarn dev

# Build for production
yarn build

# Preview production build
yarn preview

Key Features & Components

Deep Research Mode

Iterative search and analysis workflow
Uses LangChain and LangGraph for orchestration
Supports multiple search engines and web scraping
Generates comprehensive reports through recursive exploration

LLM Provider Support

The application supports multiple LLM providers configured through model.json:

OpenAI (including o1 models)
Google Gemini
DeepSeek (including R1)
Ollama, LMStudio
Various Chinese providers (Baidu, ChatGLM, Moonshot, Tencent, etc.)

Read the full file on GitHub · 127 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.

2mo ago First seen · 127 lines · 852 tokens per session scan A cbb94eba5ad7

Subscribe to this mod's changes

SearChat CLAUDE.md is an instructions file published in the GitHub repository yokingma/SearChat (1,062 stars, last pushed 2mo ago), licensed MIT. It adds 852 tokens to every session, about $0.0034 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 2026-08-30.

LLM RAG and vectors ai deepresearch search searxng

SearChat CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SearChat CLAUDE.mdyokingma/SearChat	Instructions file	1.1k	2mo ago	MIT	A	852	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

SearChat: Instructions file for Claude Code