# Claude Code Infra Showcase — Real-World Setup Patterns

> A practical showcase of Claude Code infrastructure patterns (layout, guardrails, scripts), so teams can copy defaults and standardize delivery fast.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

1. Clone:
   ```bash
   git clone https://github.com/diet103/claude-code-infrastructure-showcase
   cd claude-code-infrastructure-showcase
   ```
2. Pick one pattern and port it to your repo (start with guardrails):
   - copy the minimal instruction file(s)
   - adapt the commands to your toolchain
3. Document your “definition of done” for agents in your repo root.

## Intro

A practical showcase of Claude Code infrastructure patterns (layout, guardrails, scripts), so teams can copy defaults and standardize delivery fast.

- **Best for:** teams standardizing Claude Code usage across many repos with consistent guardrails and scripts
- **Works with:** Git + any repo; you copy patterns into your own projects and adapt commands
- **Setup time:** 20–40 minutes

## Practical Notes

- Start with 1 repo and 1 workflow (lint/test/fix) before rolling out to all repos.
- Measure impact: PR cycle time and CI failure rate usually change first.

## What to copy first (high leverage)

If you only copy one thing, copy the **guardrails**:
- what agents must run before claiming done,
- what they must never do (prod migrations, destructive ops),
- how to present output (diff, commands, verification).

## A minimal “Claude Code team standard”

1) Add a short repo instruction file:
- required commands,
- allowed directories,
- formatting expectations.

2) Provide one “happy path” script:
- run checks,
- apply fix,
- re-run checks.

3) Keep it boring:
The goal is consistent delivery, not clever prompts.

## Rollout plan

- Pilot on one repo for one week.
- Convert what worked into a template.
- Only then scale to the rest of the org.

### FAQ

**Q: Is this only for Claude Code?**
A: It’s Claude Code oriented, but most guardrail patterns apply to any coding agent.

**Q: How do I avoid prompt sprawl?**
A: Keep one canonical instruction file per repo and treat it like code (review changes).

**Q: What should I measure after rollout?**
A: CI failure rate, PR cycle time, and number of reverted agent changes.

## Source & Thanks

> Source: https://github.com/diet103/claude-code-infrastructure-showcase
> License: MIT
> GitHub stars: 9,633 · forks: 1,224

---

<!-- ZH -->

## 快速使用

1. 克隆仓库：
   ```bash
   git clone https://github.com/diet103/claude-code-infrastructure-showcase
   cd claude-code-infrastructure-showcase
   ```
2. 选一个范式迁移到你的仓库（建议先从护栏开始）：
   - 复制最小的指令文件
   - 把命令改成你们的工具链
3. 在仓库根目录写清 agent 的交付标准。

## 简介

这是一个 Claude Code 基础设施落地示例集合（目录结构、护栏规则、脚本化流程等），让团队直接复用成熟默认值并快速标准化交付；把可复现、可验证的 agent 工作流当成工程资产管理。

- **适合谁：** 在多个仓库推广 Claude Code，希望用统一护栏与脚本标准化的团队
- **可搭配：** Git + 任意仓库；你把范式复制到自己的项目并按需改造
- **准备时间：** 20–40 分钟

## 实战建议

- 先在 1 个仓库、1 条工作流（lint/test/fix）跑通，再全量铺开。
- 先看两个指标：PR 周期时间与 CI 失败率最容易出现变化。

## 最值得先抄的内容（杠杆最大）

如果你只抄一件事，就抄 **护栏**：
- agent 交付前必须跑什么，  
- 绝对不能做什么（生产迁移、破坏性操作等），  
- 输出格式如何规范（diff、命令、验证结果）。

## 一套最小“团队标准”

1）加一份简短的仓库指令文件：
- 必跑命令，  
- 允许操作的目录范围，  
- 输出格式约束。

2）提供一条“快乐路径”脚本：
- 跑检查，  
- 修复，  
- 再跑检查。

3）越朴素越好：
目标是交付一致性，不是写出花哨 prompt。

## 推广策略

- 先在 1 个仓库试运行一周。  
- 把有效做法沉淀成模板。  
- 再规模化推广到其他仓库。

### FAQ

**只适用于 Claude Code 吗？**
答：它面向 Claude Code，但大多数护栏范式适用于任何 coding agent。

**如何避免 prompt 越写越乱？**
答：每个仓库只保留一个权威指令文件，把它当代码评审。

**上线后该看什么指标？**
答：CI 失败率、PR 周期时间、以及 agent 改动被回滚的次数。

## 来源与感谢

> Source: https://github.com/diet103/claude-code-infrastructure-showcase
> License: MIT
> GitHub stars: 9,633 · forks: 1,224


---
Source: https://tokrepo.com/en/workflows/claude-code-infra-showcase-real-world-setup-patterns
Author: Skill Factory