Inside the machine
System prompts extracted from 30+ AI tools. See how they really work — token counts, costs, and techniques.
Augment
GPT-5Augment Code — GPT-5 agent prompt.
Bolt.new
StackBlitz's in-browser Node.js IDE powered by WebContainer.
ChatGPT
GPT-5ChatGPT 5 snapshot from November 2025.
Claude
Sonnet 4.6claude.ai default system prompt for Sonnet 4.6.
Claude Code
Anthropic's official CLI for Claude. Terse, tool-driven software engineering agent.
Cursor
AgentAI code editor built on VS Code. Agent mode — autonomous coding with tool use.
Devin
Cognition's autonomous software engineer. Plan/standard-mode workflow.
Dia
The Browser Company's Dia assistant.
Gemini
3.1 ProGoogle Gemini 3.1 Pro system prompt.
GitHub Copilot
ChatMicrosoft/GitHub's AI pair programmer inside VS Code.
Junie
JetBrains' Junie coding agent.
Kiro
SpecAWS's developer-focused AI IDE — Spec mode.
Lovable
AI app builder. Real-time React editing with live preview.
Manus
General-purpose agent with planner, knowledge, and data-source modules.
Microsoft Copilot
Microsoft Copilot system prompt.
Notion AI
Notion AI's latest extracted prompt.
Orchids
Orchids.app coding agent.
Perplexity
CometPerplexity Comet browser assistant.
Replit Agent
AgentReplit's autonomous programmer. Search-first, tool-driven, workflow-based.
RooCode
Open source RooCode agent.
Same.dev
Cloud IDE focused on design-to-code. Uses Bun over NPM, prefers Next.js.
Trae
BuilderByteDance's Trae IDE — Builder mode.
v0
Vercel's generative UI tool. Outputs React/Next.js with shadcn/ui.
VSCode Agent
GPT-5Microsoft's VSCode Agent — GPT-5 variant.
Windsurf
CascadeCodeium's agentic IDE. Cascade agent with memory system and batched edits.
Xcode
Apple Xcode AI coding assistant system prompt.
Understand what you're looking at
What is a system prompt?
The invisible instruction layer that turns a generic LLM into a specialized product. Why they matter, how they're paid, and why changing one line can improve your output quality.
Read guideHow to write system prompts
10 techniques used by Cursor, v0, and Claude Code — with examples from real leaked prompts. Role assignment, XML tags, chain-of-thought, tool definitions, safety rules.
Read guideWhy AI prompts leak
The three ways leaked prompts make it to GitHub: prompt injection, client-side code inspection, and network interception. What the legal/IP landscape looks like.
Read guideFrequently asked questions
What is a system prompt?
A system prompt is the hidden set of instructions given to a large language model before any user message, telling it who it is, what it can do, and how it should behave. It's what turns a generic model like Claude or GPT-4 into a specialized product like Cursor or Perplexity.
How do these system prompts get leaked?
Three common paths: (1) prompt injection attacks where users trick the model into printing its own instructions, (2) inspection of client-side JS bundles for desktop/browser AI tools, and (3) network inspection of the first API request from the tool. Community repositories collect and archive these snapshots.
Are the token counts exact?
For OpenAI-based tools (ChatGPT, GitHub Copilot, VSCode Agent's GPT variants) we use the official tiktoken library — byte-perfect. For Claude, Gemini, Grok, and DeepSeek we use a close approximation of their tokenizers. The order of magnitude is always correct; exact counts vary by a few percent.
Which AI tools are in the directory?
30 tools currently: coding agents (Cursor, Claude Code, Windsurf, v0, Replit, Lovable, Bolt, Devin, Same, Kiro, Trae, Junie, Augment, Orchids, Qoder, RooCode, Z.ai, VSCode Agent, GitHub Copilot, Xcode), chat assistants (ChatGPT, Claude, Gemini, Grok, Microsoft Copilot, Notion AI, Dia), and search/research (Perplexity, Manus). New prompts are added as they surface.
Is it legal to share these prompts?
Legal consensus is that AI system prompts aren't copyrightable in any meaningful sense — they're instructions, not creative work. Most AI companies don't pursue takedowns. WeighMyPrompt hosts community-extracted prompts with clear attribution to source repositories and welcomes requests from tool creators to correct or remove content.
Why is this useful for developers?
Reading real production system prompts is the fastest way to learn prompt engineering. You see how companies structure instructions, handle tool calling, enforce safety, and manage context. Every prompt in the directory includes detected techniques, changelog between versions, and side-by-side comparison against similar tools.
How often is the directory updated?
Prompts are synced from community repositories (x1xhlol, asgeirtj, jujumilk3) on each site update. When a new version of Cursor, Claude, or any tracked tool leaks, we add it to the manifest and re-sync.
Can I submit a prompt?
Yes. Use the Submit form at /system-prompts/submit. Submissions are reviewed before publishing — we don't publish prompts that appear fabricated. Include a source URL (tweet, GitHub, blog post) so we can verify provenance.
System prompts on this page are extracted and shared by the community from public sources. They may be incomplete, outdated, or unverified. WeighMyPrompt does not claim ownership. If you are the creator of a listed tool and want your prompt removed or updated, contact hello@weighmyprompt.com.