Announcement: Piebald is released!

We've released Piebald, the ultimate agentic AI developer experience.
Download it and try it out for free! https://piebald.ai/

_{Scroll down for Claude Code's system prompts. 👇}

This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of Claude Code v2.0.76 (December 22nd, 2025). It also contains a CHANGELOG.md for the system prompts across 57 versions since v2.0.14. From the team behind Piebald.

Why multiple "system prompts?"

Claude Code doesn't just have one single string for its system prompt.

Instead, there are:

• Large portions conditionally added depending on the environment and various configs.
• Descriptions for builtin tools like Write, Bash, and TodoWrite, and some are fairly large.
• Separate system prompts for builtin agents like Explore and Plan.
• Numerous AI-powered utility functions, such as conversation compaction, CLAUDE.md generation, session title generation, etc. featuring their own systems prompts.

The result—40+ strings that are constantly changing and moving within a very large minified JS file.

This repository contains the system prompts extracted using a script from the latest npm version of Claude Code. As they're extracted directly from Claude Code's compiled source code, they're guaranteed to be exactly what Claude Code uses. If you use tweakcc to customize the system prompts, it works in a similar way—it patches the exact same strings in your local installation as are extracted into this repository.

Note that some prompts contain interpolated bits such as builtin tool name references, lists of available sub agents, and various other context-specific variables, so the actual counts in a particular Claude Code session will differ slightly—likely not beyond ±20 tokens, however.

Sub-agents and utilities.

• Agent Prompt: Explore (516 tks) - System prompt for the Explore subagent.
• Agent Prompt: Plan mode (enhanced) (633 tks) - Enhanced prompt for the Plan subagent.
• Agent Prompt: Task tool (294 tks) - System prompt given to the subagent spawned via the Task tool.

• Agent Prompt: Agent creation architect (1111 tks) - System prompt for creating custom AI agents with detailed specifications.
• Agent Prompt: CLAUDE.md creation (384 tks) - System prompt for analyzing codebases and creating CLAUDE.md documentation files.
• Agent Prompt: Status line setup (1310 tks) - System prompt for the statusline-setup agent that configures status line display.

• Agent Prompt: /pr-comments slash command (402 tks) - System prompt for fetching and displaying GitHub PR comments.
• Agent Prompt: /review-pr slash command (243 tks) - System prompt for reviewing GitHub pull requests with code analysis.
• Agent Prompt: /security-review slash (2610 tks) - Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities.

• Agent Prompt: Agent Hook (133 tks) - Prompt for an 'agent hook'.
• Agent Prompt: Bash command file path extraction (286 tks) - System prompt for extracting file paths from bash command output.
• Agent Prompt: Bash command prefix detection (835 tks) - System prompt for detecting command prefixes and command injection.
• Agent Prompt: Bash output summarization (605 tks) - System prompt for determining whether bash command output should be summarized.
• Agent Prompt: Claude guide agent (763 tks) - System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively..
• Agent Prompt: Conversation summarization with additional instructions (1133 tks) - Extended summarization prompt with support for custom additional instructions.
• Agent Prompt: Conversation summarization (1121 tks) - System prompt for creating detailed conversation summaries.
• Agent Prompt: Prompt Hook execution (134 tks) - Prompt given to Claude when acting evaluating whether to pass or fail a prompt hook..
• Agent Prompt: Prompt Suggestion Generator v2 (296 tks) - V2 instructions for generating prompt suggestions for Claude Code.
• Agent Prompt: Session Search Assistant (444 tks) - Agent prompt for the session search assistant that finds relevant sessions based on user queries and metadata.
• Agent Prompt: Session notes template (292 tks) - Template structure for session notes tracking coding work and decisions.
• Agent Prompt: Session notes update instructions (756 tks) - Instructions for updating session notes files during conversations.
• Agent Prompt: Session title and branch generation (333 tks) - System prompt for generating succinct titles and git branch names for coding sessions.
• Agent Prompt: Update Magic Docs (718 tks) - Prompt for the magic-docs agent..
• Agent Prompt: User sentiment analysis (205 tks) - System prompt for analyzing user frustration and PR creation requests.
• Agent Prompt: WebFetch summarizer (185 tks) - Prompt for agent that summarizes verbose output from WebFetch for the main model.

Parts of the main system prompt.

• System Prompt: Main system prompt (2981 tks) - Core system prompt for Claude Code defining behavior, tone, and tool usage policies.
• System Prompt: Claude in Chrome browser automation (758 tks) - Instructions for using Claude in Chrome browser automation tools effectively.
• System Prompt: Git status (95 tks) - System prompt for displaying the current git status at the start of the conversation.
• System Prompt: Learning mode (insights) (142 tks) - Instructions for providing educational insights when learning mode is active.
• System Prompt: Learning mode (1042 tks) - System Prompt: Main system prompt for learning mode with human collaboration instructions.
• System Prompt: MCP CLI (1335 tks) - Instructions for using mcp-cli to interact with Model Context Protocol servers.
• System Prompt: Scratchpad directory (172 tks) - Instructions for using a dedicated scratchpad directory for temporary files.

Text for large system reminders.

• System Reminder: Plan mode is active (for subagents) (310 tks) - Simplified plan mode system reminder for sub agents.
• System Reminder: Plan mode is active (1211 tks) - Enhanced plan mode system reminder with parallel exploration and multi-agent planning.
• System Reminder: Plan mode re-entry (236 tks) - System reminder sent when the user enters Plan mode after having previously exited it either via shift+tab or by approving Claude's plan..

• Tool Description: AskUserQuestion (137 tks) - Tool description for asking user questions..
• Tool Description: Bash (1074 tks) - Description for the Bash tool, which allows Claude to run shell commands.
• Tool Description: Computer (161 tks) - Main description for the Chrome browser computer automation tool.
• Tool Description: Edit (278 tks) - Tool description for performing exact string replacements in files.
• Tool Description: EnterPlanMode (970 tks) - Tool description for entering plan mode to explore and design implementation approaches.
• Tool Description: ExitPlanMode v2 (450 tks) - V2 description for the ExitPlanMode tool, which presents a plan dialog for the user to approve.
• Tool Description: ExitPlanMode (342 tks) - Description for the ExitPlanMode tool, which presents a plan dialog for the user to approve.
• Tool Description: Glob (122 tks) - Tool description for file pattern matching and searching by name.
• Tool Description: Grep (300 tks) - Tool description for content search using ripgrep.
• Tool Description: LSP (255 tks) - Description for the LSP tool..
• Tool Description: MCPSearch (477 tks) - Tool description for the MCPSearch tool.
• Tool Description: NotebookEdit (121 tks) - Tool description for editing Jupyter notebook cells.
• Tool Description: ReadFile (439 tks) - Tool description for reading files.
• Tool Description: Skill (399 tks) - Tool description for executing skills in the main conversation.
• Tool Description: Task (1214 tks) - Tool description for launching specialized sub-agents to handle complex tasks.
• Tool Description: TodoWrite (2167 tks) - Tool description for creating and managing task lists.
• Tool Description: WebFetch (265 tks) - Tool description for web fetch functionality.
• Tool Description: WebSearch (334 tks) - Tool description for web search functionality.
• Tool Description: Write (159 tks) - Tool description creating/overwriting writing individual files.

Additional notes for some Tool Desscriptions

• Tool Description: Bash (Git commit and PR creation instructions) (1615 tks) - Instructions for creating git commits and GitHub pull requests.
• Tool Description: Bash (sandbox note) (454 tks) - Note about bash command sandboxing.
• Tool Description: MCPSearch (with available tools) (510 tks) - Tool description for the MCPSearch tool with available tools listed.
• Tool Description: Task (async return note) (201 tks) - Message returned to the model when a subagent launched successfully.