The library

Every prompt, annotated

Real, published system prompts from shipping AI products — each with source attribution and notes on what makes it work.

100 prompts
VSCode Agent
agent prompt

VSCode Agent (GitHub Copilot) — GPT-5 Agent Prompt

The most elaborate Copilot VS Code agent prompt, for GPT-5. It combines the Copilot identity and refusals with a detailed communication-style guide, m…

role definition tool-use protocol structured diff format specification
239 5.6k 3.7k words
AU
Augment Code
tool schema

Augment Code — Tool Schemas (Claude Sonnet 4)

JSON tool-definition file for the Augment Agent (Claude Sonnet 4 variant) defining ~22 tools: file editing (str-replace-editor with line-numbered mult…

tool schema definition constraint setting in descriptions enum constraints
229 5.4k 2.3k words
LE
Leap.new
tool schema

Leap.new — Tool Schema Definitions (JSON)

JSON tool/function schema file defining ten code-generation tools for the Leap.new app builder, including create_artifact, define_backend_service, cre…

JSON Schema tool definitions enum constraints nested object schemas
228 6.5k 1.4k words
KI
Kiro
system prompt

Kiro — Intent Mode Classifier

A lightweight intent-classification prompt that routes a user message into chat/do/spec modes and returns a JSON object of confidence scores summing t…

classification rubric constraint setting few-shot
226 5.3k 600 words
CU
Cursor
agent prompt

Cursor — Agent Prompt v1.0 (Claude Sonnet 4)

An earlier, leaner Cursor agent prompt (Claude Sonnet 4) focused on tool-calling rules, aggressive parallel tool execution, search-and-reading bias to…

role definition tool-use protocol parallel tool-call maximization
225 7.3k 1.5k words
DI
Dia
system prompt

Dia Browser AI - Chat Assistant System Prompt

System prompt for Dia, the in-browser AI assistant from The Browser Company. It defines a rich custom markup vocabulary (Simple Answers via <strong>, …

role definition custom markup protocol constraint setting
224 3.9k 2.6k words
CU
Cursor
agent prompt

Cursor — Agent Prompt (GPT-5, 2025-09-03)

A refined Cursor in-editor agent prompt (GPT-5) with tightly structured spec blocks: status_update, summary, completion, flow, tool_calling, parallel …

role definition agentic persistence directive semantic-search-first strategy
218 3.8k 3.2k words
Gemini CLI
agent prompt

Google Gemini CLI — Interactive CLI Agent System Prompt

System prompt for Google's terminal-based coding agent. It defines Core Mandates (mimic project conventions, never assume libraries, minimal comments)…

role definition tool-use protocol few-shot
216 4.2k 2.6k words
TR
Traycer AI
tool schema

Traycer AI — Plan Mode Tool Schemas

Tool schemas for Traycer's Plan mode, layering exploration tools (list_dir, file_search, grep_search, read_file, LSP navigation, get_diagnostics) with…

tool-use protocol structured JSON schema multi-agent orchestration
216 5k 1.4k words
Claude Code
tool schema

Claude Code — Tool Definitions (JSON Schema)

Machine-readable JSON array of Claude Code's 15 tool definitions, each with a descriptive prose blurb and an input_schema. Tools include Task (subagen…

tool-use protocol constraint setting few-shot
214 3.3k 5.2k words
VSCode Agent
agent prompt

VSCode Agent (GitHub Copilot) — GPT-4.1 Agent Prompt

The Copilot VS Code agent prompt for GPT-4.1, distinguished by an <applyPatchInstructions> section that mandates the apply_patch tool with a strict di…

role definition tool-use protocol structured diff format specification
209 3.7k 1.6k words
VSCode Agent
agent prompt

VSCode Agent (GitHub Copilot) — GPT-5 mini Agent Prompt

An expanded Copilot VS Code agent prompt for GPT-5 mini that adds a full software-engineering workflow: explicit mission/stop criteria, requirements-u…

role definition tool-use protocol structured diff format specification
206 684 3.1k words
Google AI Studio
system prompt

Google AI Studio — Vibe Coder (Gemini App Builder)

A prompt-to-app generator prompt that casts the model as a senior React/Gemini-API engineer producing a complete TypeScript SPA. It enforces a single …

persona output formatting constraint setting
205 6.4k 6.8k words
AU
Augment Code
agent prompt

Augment Code — Agent Prompt (GPT-5)

GPT-5 variant of the Augment Agent system prompt. Compared to the Sonnet version it adds explicit Markdown output rules, defined 'Tasklist Triggers', …

role definition tool-use protocol tool-selection routing with examples
203 8.7k 2.2k words
v0
system prompt

v0 - Vercel App Builder System Prompt

The full system prompt for Vercel's v0 assistant, covering its Vercel Sandbox workflow, dedicated file tools vs Bash, Next.js 16/React 19.2 coding gui…

role definition tool-use protocol few-shot transcripts
202 5.2k 5.4k words
Codex CLI
system prompt

Codex CLI — System Prompt (2025-08-20)

A long, dated (2025-08-20) Codex CLI system prompt with rich behavioral sections: personality/tone, preamble messages before tool calls, an update_pla…

role definition persona tool-use protocol
201 6.7k 4.8k words
Notion AI
system prompt

Notion AI — In-App Agent System Prompt

The system prompt for Notion AI, an in-app agent that runs a tool loop over a user's workspace. It defines Notion's data model (Workspace, Pages, Data…

role definition tool-use protocol constraint setting
198 5.2k 5.2k words
Notion AI
tool schema

Notion AI — Workspace Tool Schema (JSON)

A JSON tool-definition array for Notion AI's eight workspace tools: view (load entities/webpages by URL), search (a single tool with internal/web/defa…

tool-use protocol structured JSON schema few-shot
197 2.5k 4.3k words