Piebald-AI/claude-code-system-prompts

All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

What it solves

This repository provides a comprehensive, up-to-date collection of the system prompts used by Claude Code. Because Claude Code uses hundreds of different prompt strings—including conditional prompts, tool descriptions, and specialized prompts for sub-agents—it is difficult for users to see exactly how the AI is being instructed. This project extracts these strings from the compiled source code to make them transparent and accessible.

How it works

The project uses a script to extract system prompts directly from the latest npm version of Claude Code's minified JavaScript files. This ensures that the extracted prompts are identical to those used in the actual software. The repository includes a detailed changelog to track how these prompts evolve across different versions of the tool.

Who it’s for

  • AI Researchers and Prompt Engineers: Those wanting to study the complex orchestration of sub-agents and tool-use in a production-grade AI coding agent.
  • Claude Code Users: Individuals looking to understand the internal logic of the tool or those who want to customize their installation using tools like tweakcc.

Highlights

  • Extensive Coverage: Contains over 500 extracted system prompts, including those for sub-agents like Explore and Plan.
  • High Fidelity: Prompts are extracted directly from compiled source code, guaranteeing accuracy.
  • Version Tracking: Includes a changelog covering 258 versions since v2.0.14.
  • Rapid Updates: Updated within minutes of each new Claude Code release.

Related

  • Project
    wesammustafa/Claude-Code-Everything-You-Need-to-Know

    A thorough, example‑rich tutorial for Anthropic’s Claude Code CLI, covering installation, prompt engineering, and advanced extensions (Skills, Hooks, Sub‑agents, Workflows, MCP) to let developers use Claude for repo‑wide code analysis, editing, testing and automation.

  • Project
    marckrenn/claude-code-changelog

    A community-maintained archive that tracks the evolution of prompts and feature flags for Claude Code across releases.

  • Dispatch
    Mastering Claude Code: From Prompting to Programmable Engineering

    A deep dive into transforming Claude Code from a simple chatbot into a sophisticated autonomous agent using custom skills, subagents, and the Model Context Protocol.

  • Project
    nidhinjs/prompt-master

    A Claude skill that generates high-precision, token-efficient prompts for over 30 different AI tools to eliminate wasteful re-prompting.

  • Dispatch
    Claude System Prompts: Analysis of Anthropic's Model Steering

    Anthropic has released the system prompts used for Claude's web and mobile interfaces, revealing a massive increase in prompt length and a heavy reliance on hardcoded instructions for safety, identity, and behavioral steering.