agentmods.dev

cursor-rule

cursor-rule is a cursor rule for coding agents from morellid/ai-act-skill. It costs 27 tokens per session (792 once invoked), scanned A, original, MIT.

A Cursor rule for applying the European Union AI Act to AI systems built or used in the EU. It guides classification, prohibited-practice checks, and the relevant legal obligations.

In plain words
What is it for?
Use it to assess whether a system is prohibited, high-risk, covered by transparency rules, or a general-purpose AI system, and to identify provider or deployer duties.
Why use it?
It gives developers a structured way to identify which AI Act requirements may apply instead of handling every system as the same case.

Cursor rule

not rated 4 25d ago A scan 27 tokens original MIT
View the source file morellid/ai-act-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/morellid/ai-act-skill/cursor-rule
Clone the repo
git clone --depth 1 https://github.com/morellid/ai-act-skill

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cursor-rule

README.md
[![agentmods](https://agentmods.dev/badge/rules/morellid/ai-act-skill/cursor-rule.svg)](https://agentmods.dev/rules/morellid/ai-act-skill/cursor-rule)
Your own site
<a href="https://agentmods.dev/rules/morellid/ai-act-skill/cursor-rule"><img src="https://agentmods.dev/badge/rules/morellid/ai-act-skill/cursor-rule.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00792
Opus 5 $0.00014 $0.00396
Sonnet 5 $0.00005 $0.00158
Haiku 4.5 $0.00003 $0.00079

Measured 3d ago against content hash 910ba3f6f015, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-rule scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/cursor-rule.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Act Compliance — Cursor Rule

Drop this file into .cursor/rules/ai-act-compliance.mdc of your project to give Cursor structured guidance for AI Act questions. Vendor the full skill at .vendor/ai-act-skill/ (see https://github.com/morellid/ai-act-skill).

Workflow

When the user discusses AI systems built for or used in the EU, follow this order:

  1. Classify — read .vendor/ai-act-skill/tasks/classify-system.md. Determine: in scope? prohibited? high-risk? limited (Art. 50)? GPAI? Identify role: provider / deployer / importer / distributor.
  2. Check Article 5 prohibitions — .vendor/ai-act-skill/tasks/check-prohibited-practices.md. If a prohibition applies, stop and recommend redesign.
  3. Route to obligations:
    • High-risk provider: .vendor/ai-act-skill/tasks/check-high-risk-provider.md (Art. 8–22)
    • High-risk deployer: .vendor/ai-act-skill/tasks/check-deployer-obligations.md (Art. 26–27, incl. FRIA)
    • GPAI provider: .vendor/ai-act-skill/tasks/check-gpai-provider.md (Art. 51–55, 10²⁵ FLOPs threshold)
    • Article 50 transparency: .vendor/ai-act-skill/tasks/check-transparency.md

Source grounding

  • Article extracts: .vendor/ai-act-skill/references/extracts/
  • Sources catalogue: @references/sources.yaml
  • Use @file references in Cursor to pull specific extracts into context when needed.

Non-negotiable rules

  • Cite specific articles for every normative claim (e.g., "Art. 5(1)(f)", "Annex III area 4(b)").
  • If a fact is not in the extracts, do not fabricate it.
  • Always end AI Act analysis with: "support tool, not legal advice; qualified counsel review required".
  • Penalties under Article 99 reach EUR 35 million or 7% of global turnover.

Phased application calendar

Per Art. 113 as amended by Reg. (EU) 2026/1744 (Digital Omnibus on AI, in force 27 July 2026):

  • 2 Feb 2025: prohibitions (Art. 5), AI literacy (Art. 4) — IN FORCE
  • 2 Aug 2025: GPAI obligations (Ch. V), penalties, governance — IN FORCE
  • 2 Aug 2026: Art. 50 transparency and the remaining general provisions — IN FORCE
  • 2 Dec 2026: new Art. 5(1)(ba)/(bb) prohibitions (NCII, CSAM); end of the Art. 50(2) transitional period for pre-existing generative systems
  • 2 Dec 2027: high-risk Annex III stand-alone systems (Ch. III)
  • 2 Aug 2028: high-risk under Art. 6(1) (Annex I products)

Read the full file on GitHub · 52 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 52 lines · 27 tokens per session scan A 910ba3f6f015

Subscribe to this mod's changes

cursor-rule is a cursor rule published in the GitHub repository morellid/ai-act-skill (4 stars, last pushed 25d ago), licensed MIT. It adds 27 tokens to every session and 792 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsLegal and compliance
Related

Other cursor rules, from other repositories

sigma-reports

Build, validate, retrieve, and safely update Sigma report code representations through /v2/reports/spec. Use for fixed-layout or pixel-perfect reports, invoices, statements, regulatory documents, and PDF delivery. Covers report pages, absolute pixel layout, header/footer panels, common elements, verification…

twells89/sigma-skills · 92 tokens

legal-advisor

Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements.

galyarderlabs/galyarder-framework · 29 tokens

accessibility-guidelines

Accessibility guidelines for Angular + TypeScript applications to ensure inclusive design and compliance with WCAG standards.

micsapp/micstec-skills · 0 tokens

hatch3r-data-classification

Data classification standards covering PII handling, encryption, retention policies, and regulatory compliance.

hatch3r/hatch3r · 0 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens

dev-standard

Apache Superset development standards and guidelines for Cursor IDE.

apache/superset · 1,147 tokens