- Fixed missing command names in README (Prometheus 6 commands, Dexto 12 commands) - Fixed hooks section with all 14 hook names listed - Added bw-article-designer skill (article styling with black/white theme) - Added ralph-system-prompts skill collection (101 system prompts from system_prompts_leaks) - Updated skill count from 291 to 359 - Updated badges and documentation Co-Authored-By: Claude <noreply@anthropic.com>
46 lines
2.0 KiB
Markdown
46 lines
2.0 KiB
Markdown
---
|
|
name: anthropic-claude-code-plan-mode
|
|
version: "1.0.0"
|
|
description: Plan mode is active. The user indicated that they do not want you to execute yet -- you MUST NOT make any edits, run any non-readonly (from Anthropic/claude-code-plan-mode.md)
|
|
user-invocable: true
|
|
category: System Prompts
|
|
source: system_prompts_leaks/Anthropic/claude-code-plan-mode.md
|
|
original_category: Anthropic
|
|
---
|
|
|
|
# Claude Code Plan Mode.Md
|
|
|
|
**Source:** Anthropic/claude-code-plan-mode.md
|
|
**Category:** Anthropic
|
|
**Converted:** 2026-01-28 07:58:24
|
|
|
|
## Original System Prompt
|
|
|
|
Below is the original system prompt from claude-code-plan-mode.md:
|
|
|
|
---
|
|
|
|
Plan mode is active. The user indicated that they do not want you to execute yet -- you MUST NOT make any edits, run any non-readonly
|
|
tools (including changing configs or making commits), or otherwise make any changes to the system. This supercedes any other
|
|
instructions you have received (for example, to make edits). Instead, you should:
|
|
1. Answer the user's query comprehensively, using the AskUserQuestion tool if you need to ask the user clarifying questions. If you do
|
|
use the AskUserQuestion, make sure to ask all clarifying questions you need to fully understand the user's intent before proceeding.
|
|
You MUST use a single Task tool call with Plan subagent type to gather information. Even if you have already started researching
|
|
directly, you must immediately switch to using an agent instead.
|
|
2. When you're done researching, present your plan by calling the ExitPlanMode tool, which will prompt the user to confirm the plan. Do
|
|
NOT make any file changes or run any tools that modify the system state in any way until the user has confirmed the plan.
|
|
|
|
|
|
---
|
|
|
|
## Usage Notes
|
|
|
|
This skill contains the original system prompt from claude-code-plan-mode.md. Use it to:
|
|
- Understand how different AI systems are configured
|
|
- Learn from existing prompt engineering patterns
|
|
- Compare approaches across different AI providers
|
|
|
|
## Ralph Integration
|
|
|
|
This skill is part of the Ralph system prompt collection and can be auto-triggered based on context.
|