What is ZhiWei CLAUDE.md?

A set of Claude Code instructions for ZhiWei, a self-hosted AI agent system with a Spring Boot backend and Vue 3 web interface.

It helps with backend and frontend changes, AI agent workflows, memory and plugins, messaging integrations, automated tests, and local deployment.

It gives the agent the project's architecture and exact commands for building, testing, and running the backend, frontend, and Docker setup.

How ntygod/ZhiWei configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ntygod/ZhiWei. 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/ntygod/ZhiWei/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ntygod/ZhiWei

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/ntygod/zhiwei/claude-md.svg)](https://agentmods.dev/instructions/ntygod/zhiwei/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ntygod/zhiwei/claude-md"><img src="https://agentmods.dev/badge/instructions/ntygod/zhiwei/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,571 This file is loaded in full into every session.

When invoked 1,571 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	$0.01571	$0.01571
Opus 5	$0.00785	$0.00785
Sonnet 5	$0.00314	$0.00314
Haiku 4.5	$0.00157	$0.00157

Measured 7d ago against content hash 8c2f7147d509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ZhiWei 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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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

ZhiWei（知微）is a self-hosted AI Agent system with a Spring Boot backend and Vue 3 SPA frontend. It supports multi-layer memory, autonomous task execution, workflow automation, multi-channel messaging (WeChat Work, DingTalk, Feishu), and a plugin marketplace.

Build & Development Commands

Backend

mvn spring-boot:run              # Start dev server (port 8080)
mvn compile                      # Verify compilation
mvn test                         # Run JUnit 5 + jqwik tests
mvn test -Dtest=ClassName        # Run a single test class
mvn clean package -DskipTests    # Build target/zhiwei.jar

Frontend

cd zhiwei-web
npm install
npm run dev          # Vite dev server (port 5173)
npm run build        # Production build → dist/
npm run test:run     # Vitest single run

Docker

cp .env.example .env   # Configure API keys and ports first
docker compose up -d   # Start full stack

Architecture

The system is layered: Interaction → Gateway → Agent Engine → Capability Layer → Knowledge/Memory → Infrastructure → Storage.

Interaction: Web UI (Vue 3 SSE), Tauri 2.x desktop app, Channel adapters (Feishu/DingTalk/WeChat Work)
Gateway: MessageGateway with 6-stage middleware pipeline (Auth → RateLimit → Security → Router → Execution → Audit)
Agent Engine: ReactAgentLoop — ReAct-style control loop with suspend/resume, retry, and breakpoint recovery
Capability Layer: Skill system, Tool system, MCP protocol, Workflow engine, Code sandbox, Datastore
Memory: 4-layer memory (Working L1 / Episodic L2 / Semantic L3 / Procedural L4) with consolidation pipeline
Storage: SQLite with WAL mode, FTS5 full-text index, sqlite-vec for vector storage (~/.zhiwei/zhiwei.db)

Key source files:

src/main/java/com/lifepilot/agent/ReactAgentLoop.java — core agent loop
src/main/java/com/lifepilot/agent/task/CronScheduler.java — cron 定时任务调度（含 runOnce 立即执行）
src/main/java/com/lifepilot/project/service/ProjectService.java — project CRUD + 级联删除
src/main/java/com/lifepilot/interaction/web/controller/ScheduledTaskController.java — 定时任务全局管理 REST
src/main/java/com/lifepilot/generation/router/GenerationRouter.java — text generation routing with circuit breaker
src/main/java/com/lifepilot/embedding/router/EmbeddingRouter.java — embedding routing
src/main/java/com/lifepilot/rerank/router/RerankRouter.java — rerank routing
src/main/resources/application.yml — all runtime configuration
src/main/resources/db/migration/ — Flyway migration scripts; run scripts/harness/Get-FlywayLatest.ps1 before creating the next version
src/main/resources/prompts/ — StringTemplate prompt files
src/main/resources/skills/ — preset skill definitions (26 skills)
zhiwei-web/src-tauri/ — Tauri 2.x desktop app (Rust)

Read the full file on GitHub · 106 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.

7d ago First seen · 106 lines · 1,571 tokens per session scan A 8c2f7147d509

Subscribe to this mod's changes

ZhiWei CLAUDE.md is an instructions file published in the GitHub repository ntygod/ZhiWei (137 stars, last pushed 26d ago), licensed MIT. It adds 1,571 tokens to every session, about $0.0079 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.

ai-agent local-first personal-assistant spring-boot sqlite vue

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

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 · 5,182 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

ZhiWei: Instructions file for Claude Code