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.
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/yokingma/searchat/claude-mdgit clone --depth 1 https://github.com/yokingma/SearChatWrote 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/yokingma/searchat/claude-md)<a href="https://agentmods.dev/instructions/yokingma/searchat/claude-md"><img src="https://agentmods.dev/badge/instructions/yokingma/searchat/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 5.1 | $0.00852 | $0.00852 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
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 6d 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 — 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.)
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.
- 6d ago First seen · 127 lines · 852 tokens per session scan A cbb94eba5ad7
SearChat CLAUDE.md is an instructions file published in the GitHub repository yokingma/SearChat (1,059 stars, last pushed 4d ago), licensed MIT. It adds 852 tokens to every session, about $0.0043 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
mem0 AGENTS.md
AGENTS.md instructions for mem0ai/mem0, covering agents.md, do not, where to look, repository map and setup.
nosia AGENTS.md
AGENTS.md instructions for dilolabs/nosia, covering 37signals rails configuration, tech stack, architecture, core philosophy and key commands.
FastGPT AGENTS.md
AGENTS.md instructions for labring/FastGPT, covering agents.md, 项目概述, 设计文档, 架构 and packages (库代码).
obsidian-gemini-helper AGENTS.md
AGENTS.md instructions for takeshy/obsidian-gemini-helper, covering agents.md, project overview, build commands, version bumping and architecture.
obsidian-gemini-helper CLAUDE.md
Claude Code instructions for takeshy/obsidian-gemini-helper, covering claude.md, project overview, build commands, version bumping and releasing.
ai-demo AGENTS.md
Instructions for symfony/ai-demo, covering agents.md, project overview, development commands, setup and vector store must be set up before indexing.