admin/SuperCharged-Claude-Code-Upgrade
1
2
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add 179 system prompt skills and agents from major AI providers

Browse Source 
This commit adds 91 skills and 88 agents converted from the system_prompts_leaks repository.

## Stats
- Anthropic: 21 skills + 21 agents (42 total)
- OpenAI: 42 skills + 39 agents (81 total)
- Google: 11 skills + 11 agents (22 total)
- Perplexity: 2 skills + 2 agents (4 total)
- xAI: 5 skills + 5 agents (10 total)
- Proton: 2 skills + 2 agents (4 total)
- Misc: 8 skills + 8 agents (16 total)

## Features
- Auto-integrated with Ralph autonomous agent system
- Actual system prompts from production AI systems
- Includes Claude Code, GPT-5, Gemini 3, Grok 4, and more

🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
uroma
2026-01-28 08:21:52 +00:00
Unverified
parent 775bfec2d5
commit 7337f5877b
89 changed files with 25955 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
agents/anthropic-claude-code-plan-mode-agent/AGENT.md Normal file
View File

@@ -0,0 +1,20 @@
# Anthropic Claude Code Plan Mode Agent
Anthropic Claude system prompts. 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
## System Prompt
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.
---
*Created from system_prompts_leaks repository*
*Category: Anthropic Claude system prompts*