AI Companion Safety Lint (SB 243 / NY Art. 47)

Lints chatbot system-prompt and persona files for California SB 243 and New York GBL Art. 47 companion-chatbot duties: AI disclosure, break reminders, crisis referral, no fake human, no fake therapist. Runs entirely in your browser — nothing is uploaded.

Same engine as the VS Code extension, byte for byte.

Get one email when this rule changes
We watch the regulation and vendor sources behind AI Companion Safety Lint every day. When a rule changes, you get a single email with what changed and the updated check. No newsletter.

Install free

Free for the file open in your editor - no key, no limit. The workspace sweep and the report ask for a key.

Open VSX (Cursor, VSCodium)npmMCP server (npx)Docker Hub
npx @readystack/ai-companion-safety-lint <file>
npx @readystack/ai-companion-safety-lint --mcp
docker run --rm -v "$PWD:/w" getreadystack/ai-companion-safety-lint /w

Team? One key for every ReadyStack linter, 5 seats, $149 once

Get the complete version $29

This page is the working piece. The full pack has everything below.

Reads your companion chatbot's system prompt against California SB 243, New York GBL Article 47, Illinois HB 1806 (WOPR Act) and Nevada AB 406, line by line.

Outside privacy counsel reviews prompt text at roughly $400 an hour

Buy the full version — $29

Questions people ask

What does AI Companion Safety Lint actually do?

It reads the system-prompt, persona and character-card files in your workspace and reports every line that breaks a California SB 243, New York Article 47, Illinois HB 1806 or Nevada AB 406 duty, plus every duty the file never states at all. Each finding carries a line number and the statute section. 14 rules, all local to the editor.

Who is this for?

Developers and small studios shipping companion, character or roleplay chatbots to users in the United States, and the person who has to answer an app-store or counsel question about the prompt. If your repo holds persona files a model wrote, this is aimed at you rather than at a compliance department.

Why not just ask a chatbot whether my prompt is compliant?

A chatbot summarises statutes well, but it cannot open the prompt and persona files scattered across your repository, name the line that tells the bot to deny being an AI, and give the same answer twice. This runs the same 14 rules over every file every time and prints line numbers you can jump to.

What is free and what needs a licence key?

The scan is free and complete: every file in the workspace, every finding, its line and its statute section, with no key and no limit. The key adds a different thing - a dated evidence pack that writes every file, finding, section and rule-set version into one Markdown or JSON artifact you keep and diff between releases.

What would this cost done by a person?

Outside privacy counsel reviews prompt text at roughly $400 an hour, and a companion app usually has more than one persona file. SB 243 itself sets the downside: a private right of action for the greater of actual damages or $1,000 per violation, plus attorney's fees, in force since 2026-01-01.

Ask about this tool

One question, answered by the person who built it. Your email only if you want the answer sent.

ENDEJAESPT

Find a tool