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.
npx skills add RashadAnsari/myagents --skill eu-ai-actgit clone --depth 1 https://github.com/RashadAnsari/myagentsWrote 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/skills/rashadansari/myagents/eu-ai-act)<a href="https://agentmods.dev/skills/rashadansari/myagents/eu-ai-act"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/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/skills/rashadansari/myagents/eu-ai-act"><img src="https://agentmods.dev/badge/skills/rashadansari/myagents/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 | $0.00091 | $0.02008 |
| Opus 5 | $0.00046 | $0.01004 |
| Sonnet 5 | $0.00018 | $0.00402 |
| Haiku 4.5 | $0.00009 | $0.00201 |
Grade A, and why
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EU AI Act
Working knowledge of Regulation (EU) 2024/1689 (the EU AI Act). Use it to answer questions and assess whether a system, feature, or product is in scope and what obligations apply.
Freshness rule (read first)
The implementation timeline was amended by the "Digital Omnibus on AI" package: adopted by Parliament on 16 June 2026, approved by Council on 29 June 2026, and signed on 8 July 2026. Official Journal publication was expected before 2 August 2026, with entry into force on the third day after publication. If advice depends on the amendments being in force, verify publication via web search (query: "Digital Omnibus AI Official Journal"). Prefer primary sources: digital-strategy.ec.europa.eu and ai-act-service-desk.ec.europa.eu. Warn users that most guidance published before mid-2026 describes deadlines that no longer apply.
What the Act is
- The EU's comprehensive AI regulation, the first of its kind. Entered into force 1 August 2024, applying in stages.
- Extraterritorial: applies to providers and deployers outside the EU if the AI system's output is used in the EU (sales, access, downstream integrations).
- Not retroactive: systems already on the market before a given obligation applies may be grandfathered for certain obligations, unless significantly redesigned afterwards.
Risk tiers
- Prohibited practices (banned since 2 February 2025): social scoring by public authorities, manipulative or exploitative AI, untargeted scraping of facial images, emotion recognition in workplaces and schools (with narrow exceptions), most real-time remote biometric identification in public spaces. The Omnibus adds a prohibition on AI systems that generate non-consensual intimate imagery or child sexual abuse material, including general-purpose image and video tools where such output is a reasonably foreseeable and reproducible outcome; providers must implement refusal training, output controls, and content filtering. Compliance deadline: 2 December 2026.
- High-risk systems: two families.
- Annex III stand-alone systems: biometrics, critical infrastructure, education, employment and worker management, access to essential services and credit, law enforcement, migration/asylum/border control, administration of justice.
- Annex I embedded systems: AI as a safety component of products already covered by EU product law (medical devices, vehicles, toys, etc.), via Article 6(1). The Omnibus narrows this family: AI used solely for user assistance, performance optimization, service efficiency, automation or convenience, or quality control is not automatically a safety component unless its failure poses health or safety risks, and AI embedded in Machinery Regulation products is largely excluded from the high-risk regime (the Commission can reintroduce AI-specific requirements via delegated acts). Medical devices and toys remain fully in scope.
- Obligations: risk management system, data governance, technical documentation, logging, human oversight, accuracy/robustness/ cybersecurity requirements, conformity assessment, CE marking, registration in the EU database.
- Limited risk: transparency obligations only (Article 50, below).
- Minimal or no risk: no new obligations. Most AI systems in use (spam filters, game AI, routine ML features) fall here.
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.
- 11d ago First seen · 163 lines · 91 tokens per session scan A bf82d61d9b86
eu-ai-act is a skill published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 2,008 once invoked, about $0.0005 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.
Other skills, from other repositories
feedoracle-mcp
FeedOracle provides real-time MiCA regulatory compliance and RWA risk intelligence for AI agents. It monitors 18 MiCA articles across 80+ stablecoins and RWA protocols. Every response uses an identical JSON schema with status taxonomy, evidence classes, HMAC signature, and verify URL.
systemprompt-tools
Call the free systemprompt.io tools API from any agent: EU AI Act risk classification, CLAUDE.md scoring, llms.txt/AGENTS.md generation and validation, GitHub Actions permissions, and AI ROI calculation. No API key, no signup.
security-documentation
Master security documentation with security policies, incident response plans, security procedures, and compliance documentation.
compliance-management
Master compliance management with GDPR, SOC 2, ISO 27001, audit preparation, and regulatory requirements.
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.