# Claude Code Prompts — 26 Agent Prompt Templates

> Independently authored collection of 26 prompt templates for AI coding agents — system prompts, tool routing, agent delegation, memory management, and multi-agent coordination patterns. MIT license.

## Install

Paste the prompt below into your AI tool:

## Quick Use

1. Browse the templates: [github.com/repowise-dev/claude-code-prompts](https://github.com/repowise-dev/claude-code-prompts)
2. Copy the prompt template for your use case
3. Paste into your AI agent's system prompt or configuration
4. Replace placeholder values with your specific stack details

For Cursor IDE: move the `skills/` directory to `~/.cursor/skills-cursor/`

---

## Intro

Claude Code Prompts is an independently authored collection of 26 complete prompt templates for building AI coding agents, with 750+ GitHub stars and MIT license. It documents patterns observed in Claude Code's behavior — safety rules, tool routing, agent delegation, and memory management — then provides original, production-ready prompt implementations. Unlike leaked system prompts, these are clean-room recreations designed to be understood, modified, and used in your own agent systems.

Best for: developers building custom AI coding agents or customizing Claude Code / Cursor behavior.
Works with: Claude Code, Cursor, any LLM-based coding agent.
Setup time: copy-paste, under 5 minutes.

---

## Claude Code Prompts — Template Categories

### System Prompts (1 template)

The core agent identity prompt that defines:
- Agent role and behavioral rules
- Safety constraints and risk assessment
- Permission boundaries
- Communication style

### Tool Prompts (11 templates)

| Template | Purpose |
|----------|---------|
| Shell Execution | Safe command execution with sandboxing rules |
| File Read | Context-aware file reading with line ranges |
| File Write | New file creation with safety checks |
| File Edit | Surgical string replacement in existing files |
| Search (Glob) | Fast pattern-based file discovery |
| Search (Grep) | Content search with regex support |
| Web Fetch | URL content retrieval and processing |
| Web Search | Internet search with source attribution |
| Agent Launch | Spawning sub-agents for parallel tasks |
| User Query | Interactive question-asking with context |
| Planning Mode | Task decomposition and plan approval |

### Agent Prompts (5 templates)

| Template | Purpose |
|----------|---------|
| General Purpose | Default agent for multi-step tasks |
| Code Explorer | Fast codebase navigation and search |
| Architecture Planner | System design and implementation planning |
| Verification Tester | Testing and quality assurance |
| Documentation Agent | Code documentation generation |

### Memory Prompts (4 templates)

| Template | Purpose |
|----------|---------|
| Conversation Summarizer | Compress long conversations |
| Session Tracker | Track progress across context windows |
| Memory Extractor | Extract persistent learnings |
| Memory Consolidator | Merge and deduplicate memories |

### Coordination (1 template)

Multi-agent orchestrator that manages task delegation, progress tracking, and result synthesis across parallel agent teams.

### Utility Prompts (4 templates)

Session titling, action summaries, conversation recaps, and next-step suggestions.

### Design Principles

The templates follow key architectural patterns:

1. **Safety-First** — Every tool prompt includes risk assessment and confirmation rules
2. **Minimal Context** — Prompts are optimized to use minimum tokens while maintaining behavior
3. **Composable** — Mix and match templates to build custom agent configurations
4. **Observable** — Built-in action logging and explanation patterns

### FAQ

**Q: What is Claude Code Prompts?**
A: A collection of 26 independently authored prompt templates that recreate the architectural patterns of AI coding agents — system prompts, tool routing, agent delegation, memory management, and multi-agent coordination.

**Q: Is this the same as leaked system prompts?**
A: No. These are clean-room recreations — original implementations inspired by observed behavior patterns, designed to be understood and modified. Not copies of proprietary prompts.

**Q: Can I use these in my own agent?**
A: Yes, MIT license. Copy, modify, and use in any project.

---

## Source & Thanks

> Created by [RepoWise](https://github.com/repowise-dev). Licensed under MIT.
>
> [claude-code-prompts](https://github.com/repowise-dev/claude-code-prompts) — ⭐ 750+

Thank you to the RepoWise team for documenting and open-sourcing these agent prompt patterns.

---

<!-- ZH -->

## 快速使用

1. 浏览模板：[github.com/repowise-dev/claude-code-prompts](https://github.com/repowise-dev/claude-code-prompts)
2. 复制适合你用例的 prompt 模板
3. 粘贴到你的 AI Agent 系统提示或配置中
4. 替换占位符值

---

## 简介

Claude Code Prompts 是一个独立编写的 26 个 AI 编程 Agent 提示模板集合，拥有 750+ GitHub Star 和 MIT 许可证。它记录了在 Claude Code 行为中观察到的模式——安全规则、工具路由、Agent 委派和记忆管理——然后提供原创的、可直接用于生产的提示实现。

适合人群：构建自定义 AI 编程 Agent 或自定义 Claude Code / Cursor 行为的开发者。
兼容工具：Claude Code、Cursor、任何基于 LLM 的编程 Agent。

---

## 模板分类

- **系统提示**（1 个）：Agent 身份、行为规则、安全约束
- **工具提示**（11 个）：Shell 执行、文件操作、搜索、网页获取、Agent 启动
- **Agent 提示**（5 个）：通用、代码探索、架构规划、验证测试、文档
- **记忆提示**（4 个）：对话压缩、会话追踪、记忆提取、去重合并
- **协调提示**（1 个）：多 Agent 编排
- **工具提示**（4 个）：会话标题、操作摘要、回顾、建议

### FAQ

**Q: Claude Code Prompts 是什么？**
A: 26 个独立编写的 AI 编程 Agent 提示模板，覆盖系统提示、工具路由、Agent 委派和多 Agent 协调。

**Q: 免费吗？**
A: MIT 开源免费。

---

## 来源与感谢

> Created by [RepoWise](https://github.com/repowise-dev). Licensed under MIT.
>
> [claude-code-prompts](https://github.com/repowise-dev/claude-code-prompts) — ⭐ 750+

---
Source: https://tokrepo.com/en/workflows/5335df26-ac23-46d7-89f6-2306a52d2bcb
Author: Prompt Lab