repowiserepowise-dev/claude-code-prompts

repowise-dev / claude-code-prompts

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

★ 1,216
Use in your agentAsk this codebase

github.com/repowise-dev/claude-code-promptsIndexed at 989fc0eUp to date with upstreamRefreshes on every push

What is claude-code-prompts?

claude-code-prompts is a collection of independently authored prompt templates for building AI coding agents. It provides prompts for agent behavior, tool use, delegation, memory management, verification, and multi-agent coordination. The repository is primarily a collection of Markdown prompt files, with Cursor skills included.

Written by a model from the README and the source

44 files and 0 symbols in 0 modules.

Start reading

Code health

Health scores land with the first index: complexity, duplication, coverage, churn and ownership across every file.

Use repowise-dev/claude-code-prompts in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/repowise-dev/claude-code-prompts
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is claude-code-prompts put together?")
  • get_why("why is claude-code-prompts structured this way?")

Explore claude-code-prompts

Key features of claude-code-prompts

  • System prompts define agent identity, safety rules, code style, tool routing, and output format.
  • Tool prompts cover shell execution, file operations, search, web access, agent launching, user questions, and planning.
  • Agent prompts support general-purpose work, code exploration, solution architecture, verification, and documentation.
  • Memory prompts cover conversation summaries, session notes, memory extraction, and memory consolidation.
  • The collection includes a coordinator prompt for multi-worker orchestration with synthesis, delegation, and verification.
  • Cursor skills provide coding standards, verification workflows, and prompt design guidance.

How repowise-dev/claude-code-prompts works

The repository organizes reusable prompt material into complete-prompts, patterns, skills, and root files. Files in complete-prompts provide system, tool, agent, memory, coordinator, and utility prompts that can be copied into an AI coding agent configuration. Files in patterns explain prompt structures and provide reusable templates for safety, tool routing, delegation, verification, memory, and coordination. The skills directory provides drop-in Cursor IDE skills for coding standards, verification, and prompt design. Users replace placeholder values in the prompts with their own stack, tool names, and risk policy.

The codebase has 44 files and 0 symbols in 0 modules.

repowise-dev/claude-code-prompts FAQ

What is claude-code-prompts?

claude-code-prompts is a collection of independently authored prompt templates for AI coding agents. It covers system behavior, tools, agents, memory, verification, and multi-agent coordination.

How does claude-code-prompts work?

claude-code-prompts provides complete prompts that users copy into agent configurations. Users adapt placeholder values for their stack, tools, and risk policy.

What language is claude-code-prompts written in?

claude-code-prompts is primarily written as Markdown prompt content. The repository also includes Cursor skills.

How is the claude-code-prompts code organized?

claude-code-prompts is organized into complete-prompts, patterns, skills, and root files. Complete prompts cover agent workflows, patterns explain reusable structures, and skills support Cursor IDE.

When should I use claude-code-prompts?

Use claude-code-prompts when building or configuring an AI coding agent. The templates address safety, tool routing, delegation, verification, memory, and coordination.

What license does claude-code-prompts use?

claude-code-prompts uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of repowise-dev/claude-code-prompts from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.