Prompt Token Analyzer for Openclaw

To get started with this tool from the Openclaw Skills collection, first install the necessary tokenizer dependency:

npm install -g gpt-tokenizer

Next, create the executable script by running the following command in your terminal:

cat <<'EOF' > prompt-token
#!/usr/bin/env node

import { encode } from "gpt-tokenizer"
import fs from "fs"

const args = process.argv.slice(2)

if (args.length === 0) {
  console.log("Usage:")
  console.log("  prompt-token analyze <file>")
  console.log("  prompt-token text \"your prompt here\"")
  process.exit(1)
}

let text = ""

if (args[0] === "analyze") {
  const file = args[1]
  if (!file) {
    console.error("Missing file path")
    process.exit(1)
  }
  text = fs.readFileSync(file, "utf8")
} else if (args[0] === "text") {
  text = args.slice(1).join(" ")
} else {
  console.error("Unknown command")
  process.exit(1)
}

const tokens = encode(text)

console.log("Prompt Token Analysis")
console.log("---------------------")
console.log("Characters:", text.length)
console.log("Tokens:", tokens.length)
console.log("Average chars/token:", (text.length / tokens.length).toFixed(2))

const estimatedCost = tokens.length / 1000000 * 5

console.log("")
console.log("Estimated cost (example $5 / 1M tokens):")
console.log("$" + estimatedCost.toFixed(6))
EOF

Finally, make the script executable and move it to your system PATH:

chmod +x prompt-token
sudo mv prompt-token /usr/local/bin/

The Prompt Token Analyzer processes text input and generates a structured statistical report. It handles data according to the following schema: