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.
git clone --depth 1 https://github.com/legalithm-org/legalithmWrote 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.
[](https://agentmods.dev/rules/legalithm-org/legalithm/legalithm-eu-ai-act)<a href="https://agentmods.dev/rules/legalithm-org/legalithm/legalithm-eu-ai-act"><img src="https://agentmods.dev/badge/rules/legalithm-org/legalithm/legalithm-eu-ai-act/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/legalithm-org/legalithm/legalithm-eu-ai-act"><img src="https://agentmods.dev/badge/rules/legalithm-org/legalithm/legalithm-eu-ai-act.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00297 |
| Opus 5 | $0.00000 | $0.00148 |
| Sonnet 5 | $0.00000 | $0.00059 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
legalithm-eu-ai-act 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 12d 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.
What it actually says
EU AI Act rules (Legalithm)
This project ships AI into the EU, so the EU AI Act applies. When you add or change AI features:
- Classify first. Use the
legalithmMCPclassifytool to determine the risk tier (unacceptable / high / limited / minimal) before building. - Article 50 transparency. For user-facing AI (chatbots, generated content, deepfakes, emotion recognition), add a transparency disclosure. Generate one with the
generate_disclosuretool — don't hand-write legal text. - Frame outputs as checked against Regulation (EU) 2024/1689 — not legal advice. Never claim "instant compliance" or "compliant by default."
- Map to named obligations, not fear copy. Use
explain_obligationfor the actual duties (with Article citations), e.g. Article 9 risk management, Article 10 data governance. - Keep the record current.
compliance/legalithm.jsonis the committed compliance record. Runnpx legalithm checkbefore shipping; if it reports drift, re-runinitand review.
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.
- 12d ago First seen · 17 lines · 0 tokens per session scan A 4263e34f4a65
legalithm-eu-ai-act is a cursor rule published in the GitHub repository legalithm-org/legalithm (0 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 297 tokens. 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.
Other cursor rules, from other repositories
hatch3r-data-classification
Data classification standards covering PII handling, encryption, retention policies, and regulatory compliance.
legal-advisor
Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.