A static analyzer for LLM prompts. Catches injection attacks, token waste, and structural issues before they hit production — zero API calls, zero latency.
[*] free on VS Code marketplace · launching soon
Squiggly underlines on bad prompts. Lightbulb auto-fix for safe changes. Works just like ESLint.
One command. Works as a pre-commit hook or GitHub Action. Fails builds on CRITICAL issues.
Purely deterministic parsing. No LLM round-trip. No API key needed. Results in milliseconds.
Safe changes applied automatically. Ambiguous rewrites shown as suggestions you approve first.
Get notified when PromptLint hits the VS Code Marketplace.