Skip to content

System Prompt Editor & Analyzer

Write and analyze AI system prompts with live token counting, variable detection, and XML highlighting

System Prompt Editor & Analyzer

Start with a template

Stats

Characters

436

Words

62

Lines

13

Estimated tokens (claude)

125

Context limits

4K4,096
8K8,192
16K16,384
32K32,768
65K65,536
128K128,000
200K200,000

Variables detected

retrieved_documents1×
user_query1×
Pro tips: Use XML tags like <system>, <context>, and <instructions> to structure your prompt. Define variables with {{variable}} syntax.

Updated . Provided as is. Check the output before you rely on it in production.

How to use System Prompt Editor & Analyzer

  1. 1

    Write or paste your prompt

    Enter a system prompt from scratch or paste an existing one. The editor provides syntax highlighting and keeps your text organized.

  2. 2

    Monitor token count

    The tool shows real-time token count as you type. Keep system prompts under 500-1000 tokens to preserve context for actual conversation. Switch between token counter models if needed.

  3. 3

    Analyze prompt structure

    Well-structured prompts follow: Role/Goal → Instructions → Examples → Output Format. Use the editor to reorganize and clarify. Test edge cases in your instructions.

  4. 4

    Test prompt quality

    Paste your prompt into an AI interface and test it with real queries. Note any ambiguities, unclear instructions, or unexpected behaviors. Refine based on actual results.

Questions and answers

What is System Prompt Editor?
A system prompt is the instruction block a model receives before the conversation, defining its role, rules and output format. This editor estimates its tokens for Claude, GPT, Gemini and Llama from character ratios, warns near context limits, detects {{variable}} placeholders, highlights XML tags and loads templates.
Does System Prompt Editor store or send my data?
No. All processing happens entirely in your browser. Your prompts stay on your device — nothing is sent to any server.
Which AI models does System Prompt Editor count tokens for?
It estimates token counts for major models including Claude, GPT, and Gemini. This helps you stay within context window limits when designing system prompts.
For AI agents: how to call this tool

Machine-readable contract, endpoints and examples. Humans can ignore this section.

Best Path For Builders

Browser workflow

Runs instantly in the browser with private local processing and copy/export-ready output.

Browser Workflow

This tool is optimized for instant in-browser execution with local data handling. Run it here and copy/export the output directly.

/system-prompt-editor/

For automation planning, fetch the canonical contract at /api/tool/system-prompt-editor.json.