Cette page est affichée en anglais. Une traduction française est en cours.
PromptsMar 28, 2026·3 min de lecture

System Prompts — Extracted from 30+ AI Coding Tools

Full system prompts extracted from Claude Code, Cursor, Devin, Windsurf, Replit, v0, and 25+ more AI tools. See exactly how they work.

Prompt Lab
Prompt Lab · Community
Prêt pour agents

Installation agent prête

Cet actif peut être installé après choix du runtime, vérification du plan et exécution de la commande adaptée.

Native · 96/100Policy : autoriser
Surface agent
Tout agent MCP/CLI
Type
Prompt
Installation
Single
Confiance
Confiance : Community
Point d'entrée
System Prompts of Top AI Coding Tools
Commande d'installation directe
npx -y tokrepo@latest install 6f1ca496-3956-4b11-b736-b13572fc53a0 --target codex

À exécuter après confirmation du plan en dry-run.

TL;DR
Read the exact system prompts used by Claude Code, Cursor, Devin, and 25+ other AI tools.
§01

What it is

This collection contains full system prompts extracted from 30+ AI coding tools including Claude Code, Cursor, Devin, Windsurf, Replit, v0, and others. Each prompt reveals the exact instructions that shape how these AI assistants behave, what constraints they follow, and what capabilities they expose.

The collection targets prompt engineers, AI researchers, and developers who want to understand how commercial AI tools are built and learn prompt design patterns from production systems.

§02

How it saves time or tokens

Studying production system prompts saves weeks of trial-and-error in prompt engineering. You see proven patterns for instruction following, tool use formatting, safety guardrails, and output structuring used by the best AI products. Adapting these patterns to your own agents is faster than designing from scratch.

§03

How to use

  1. Browse the collection to find prompts from the tools you are interested in.
  2. Study the structure: system context, behavioral constraints, tool definitions, and output formatting.
  3. Adapt patterns to your own AI applications and agent configurations.
§04

Example

# Common patterns found across AI tool system prompts:
§05

1. Role definition

'You are an expert software engineer...'

§06

2. Behavioral constraints

'Never modify files without user approval.'

'Always explain changes before making them.'

§07

3. Tool use formatting

'When using tools, follow this exact JSON schema...'

§08

4. Safety guardrails

'Do not execute destructive operations.'

'Ask for confirmation before deleting files.'

§09

5. Output structure

'Respond with a brief summary followed by code blocks.'

§10

Related on TokRepo

§11

Common pitfalls

  • System prompts change frequently. The extracted versions represent a point-in-time snapshot and may not match the current production version.
  • Copying an entire system prompt verbatim is less useful than understanding the underlying patterns. Adapt the principles rather than the exact text.
  • Some extracted prompts may be incomplete or from beta versions. Cross-reference with official documentation when available.

Questions fréquentes

How are these system prompts extracted?+

System prompts are extracted through various methods including prompt injection techniques, API response inspection, browser developer tools, and community reverse engineering. The exact method varies by tool.

Are these prompts the latest versions?+

Not necessarily. AI tools update their system prompts regularly. The collection represents snapshots at the time of extraction. Check the collection's update dates for recency.

Can I use these prompts in my own projects?+

The prompts reveal patterns and techniques you can learn from. However, directly copying a commercial product's system prompt may raise intellectual property concerns. Adapt the patterns to your own context.

Which AI tools are included?+

The collection includes prompts from Claude Code, Cursor, Devin, Windsurf, Replit, v0, GitHub Copilot, and 25+ other AI coding and development tools. Coverage depends on community contributions.

What can I learn from studying system prompts?+

You learn how production AI tools structure instructions, handle edge cases, format tool calls, implement safety guardrails, and guide output quality. These patterns are directly applicable to building your own AI applications.

Sources citées (3)
En lien sur TokRepo
Prompt LibraryAI Coding ToolsFeatured workflows
🙏

Source et remerciements

Created by x1xhlol. Licensed under GPL-3.0. system-prompts-and-models-of-ai-tools — ⭐ 134,000+

Thanks to x1xhlol for maintaining the most complete archive of AI tool system prompts.

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires

Awesome AI System Prompts — 32+ Tool Prompts Revealed

Curated collection of extracted system prompts from 32+ production AI tools including ChatGPT, Claude, Cursor, v0, Manus, Devin, Windsurf, and Perplexity. MIT license, 5,700+ stars.

Prompts
Prompt Lab

Vibe Coding Template — 5-Step Prompts for Shipping

Vibe Coding Template provides five prompts (research → PRD → tech design → agent files → build) to make AI-assisted shipping structured.

Prompts
Prompt Lab

Prompt Architect — 27 Frameworks for Expert Prompts

Transform vague prompts into structured, expert-level prompts using 27 research-backed frameworks across 7 intent categories. Works with Claude Code, ChatGPT, Cursor, and 30+ AI tools.

Prompts
Prompt Lab

Claude Code System Prompts — Full Extraction

Complete extraction of all Claude Code system prompts, 18 tool descriptions, sub-agent prompts, and utility prompts. Tracked across 135+ versions.

Prompts
Prompt Lab
◈Accueil🔍Rechercher👤Moi