build-claude-code — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by OPBR · Agent Tool · ★ 136

Last updated: 2026-09-20 · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is build-claude-code safe to install? View the security audit →

About build-claude-code

Build Claude Code 中文 | English 从0到1构建 Claude Code 风格的 AI Coding Agent 简介这是一个渐进式学习项目，用 TypeScript 从零开始构建一个完整的 AI 编程代理。我们将逐步实现 Claude Code 的所有核心机制：本项目灵感来自 learn-claude-code（59.7k ⭐），原项目 Agent 核心由 Python 实现，本项目使用 TypeScript 重写 Agent 逻辑本身，目前已完成 s01–s13，持续更新中。适合希望在 Node.js / TypeScript 生态中深入理解 Harness 工程的开发者。核心循环工具系统任务规划上下文压缩多代理协作工作树隔离核心理念：智能来自模型训练，Harness（套件）只是让智能得以表达的载体。我们构建的是载体，不是智能本身。学习路线 Background Ta

agent agent-design ai-agent claude-code teaching typescript

Quick Facts

Stars	136
Forks	18
Language	TypeScript
Category	Agent Tool
Quality Score	60.5654508736216/100
Last Updated	2026-09-20
Created	2026-04-19
Platforms	claude-code, node
Est. Tokens	~15k

Compatible Skills

These tools work well together with build-claude-code for enhanced workflows:

Claw-ED — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
claude-skills — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
styleseed — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
Claude-Zeroclaw — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
melta-ui — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

build-claude-code alternative? Top 6 similar tools

Looking for a build-claude-code alternative? If you're comparing build-claude-code with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

Overture by SixHq · ⭐ 630
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
claudex by Mng-dev-ai · ⭐ 224
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
deterministic-agent-control-protocol by elliot35 · ⭐ 89
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
wcgw by rusiaaman · ⭐ 674
Shell and coding agent on mcp clients
dexto by truffle-ai · ⭐ 650
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
Mantic.sh by marcoaapfortes · ⭐ 555
A structural code search engine for Al agents.

More Agent Tool Tools

Explore other popular agent tool tools:

awesome-claude-code ⭐ 54.4k
open-saas ⭐ 15.8k
notebooklm-skill ⭐ 7.8k
playwright-skill ⭐ 3.0k
skills ⭐ 2.0k
agent-skills ⭐ 6.5k
raptor ⭐ 3.8k
excalidraw-diagram-skill ⭐ 4.3k
chinese-novelist-skill ⭐ 2.8k
claude-code-skill-factory ⭐ 844

View all Agent Tool tools →

Popular TypeScript Agent Tools

n8n ⭐ 205.5k · MCP Server
gemini-cli ⭐ 107.1k · MCP Server
context7 ⭐ 62.2k · MCP Server
UI-TARS-desktop ⭐ 38.9k · MCP Server
chrome-devtools-mcp ⭐ 52.3k · MCP Server

Frequently Asked Questions

What is build-claude-code?

build-claude-code is 从0到1构建 Claude code (学习版). It is categorized as a Agent Tool with 136 GitHub stars.

What programming language is build-claude-code written in?

build-claude-code is primarily written in TypeScript. It covers topics such as agent, agent-design, ai-agent.

How do I install or use build-claude-code?

You can find installation instructions and usage details in the build-claude-code GitHub repository at github.com/OPBR/build-claude-code. The project has 136 stars and 18 forks, indicating an active community.

What are the best alternatives to build-claude-code?

The top alternatives to build-claude-code on Agent Skills Hub include Overture, claudex, deterministic-agent-control-protocol. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools