Rules that now apply to AI features and the agents that build them: disclosure and companion-safety laws, MCP server and client configuration, model retirement dates and AI crawler access. The linters read your code and config locally.
The checks
Model Card Lint - EU GPAI (AI Act Art. 53)
Lints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI documentation duties, line by line.
MCP Server Config Audit
Audit one mcp.json for what an agent config gives away — inline API keys, unpinned npx launches, plaintext remote servers, shell wrappers, auto-approved tools, whole-machine filesystem roots — with line numbers. The shipped sample config _fixtures/dirty.mcp.json (33 lines, five servers) returns 14 findings, 8 of them blocking.
AI Model License Lint
Reads the open-weight model IDs in your code and names the licence clause that binds you - 22 rules, 17 findings on a 33-line fixture
Agentforce Action Audit
13 rules on a Salesforce Agentforce topic file, before the deploy and before Article 50
AI Crawler Rules - robots.txt Audit for AI Search
Checks robots.txt line by line and says what each AI crawler token actually controls - training, AI-search citation, or user fetch - and which lines silently do nothing.
SaaS UI Kit — AI Act Article 50 Chatbot Notices & AI Labels (Figma)
8 components, 26 variants for the AI features of a SaaS product: the 'you're chatting with an AI' notice, AI-generated labels and the human handoff. EU AI Act Art. 50 applies since 2 August 2026, with fines up to €15,000,000 or 3% of worldwide turnover (Art. 99(4)). Sketch users open the same file.
SaaS UI Kit — AI Disclosure Labels for EU AI Act Art. 50 & California SB 942 (Figma + Sketch)
SaaS UI kit for AI features: EU AI Act Article 50 applies since 2 August 2026, with fines up to €15,000,000 or 3% of turnover. 8 components, 27 variants: AI labels, chatbot notice, export toggle.
AI Output Disclosure Lint SB 942
Finds the generative-AI code that drops the disclosures California SB 942 has required since August 2, 2026.
AI Companion Safety Lint
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.
MCP Config Guard - agent config lint
Reads .mcp.json / .vscode/mcp.json / claude_desktop_config.json while you edit it and marks the lines that hand an AI agent more than you meant - unpinned servers, literal credentials, plaintext transport, whole-home filesystem roots. 23 rules, offline, no server is ever started.
MCP 2026 Migration Lint
The 2026-07-28 MCP revision removed the initialize handshake, sessions, ping and 4 more RPCs. 27 rules find them in your mcp.json and server code, with the replacement on each line.
AI Model Retirement Lint
Finds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to switch off, with the replacement and the date.
EU AI Act Article 50 Transparency Audit for Your Codebase
Finds the AI call sites, generation code and system prompts that trigger EU AI Act Article 50 disclosure duties - in force since 2 August 2026.
How they run
Every check runs on your machine — in the editor, the browser or CI — and your files are not uploaded. Each tool is free for the file or case in front of you; the paid part is a one-time licence key, and a team key opens every linter for five seats and CI.
The full list
All 13, with install links for VS Code, Chrome, Edge, Firefox, npm and Docker: https://getreadystack.com/collections/ai-rules-and-agents?ref=devto
Top comments (0)