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 CSOAI-ORG/csoai-static-deploy2 --skill eu-ai-act-art50git clone --depth 1 https://github.com/CSOAI-ORG/csoai-static-deploy2Wrote 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/csoai-org/csoai-static-deploy2/eu-ai-act-art50)<a href="https://agentmods.dev/skills/csoai-org/csoai-static-deploy2/eu-ai-act-art50"><img src="https://agentmods.dev/badge/skills/csoai-org/csoai-static-deploy2/eu-ai-act-art50/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/csoai-org/csoai-static-deploy2/eu-ai-act-art50"><img src="https://agentmods.dev/badge/skills/csoai-org/csoai-static-deploy2/eu-ai-act-art50.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 | $0.00100 | $0.00558 |
| Opus 5 | $0.00050 | $0.00279 |
| Sonnet 5 | $0.00020 | $0.00112 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
eu-ai-act-art50-check 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.
What it actually says
EU AI Act Article 50 — transparency check
The doc's #1 discovery rail: an installable Agent Skill that RUNS the check instead of
hallucinating the statute. It wraps the canonical csoai CLI — it does not reimplement
the grader.
When to use
A user (or agent) asks: "is model X compliant with Article 50?", "check this model's
transparency", "audit <hf-repo> for the EU AI Act", "does this model declare provenance?".
How to run
pip install csoai # once
scripts/check.sh <hf-model-repo-id>
# e.g. scripts/check.sh gpt2
Output: a JSON card with the transparency predicates, the pack_result (pass/missing),
and a state_hash. Exit code 0 = compliant-shaped; 3 = a required transparency
predicate is MISSING (a CI gate can fail the build on 3).
What it measures (deterministic, no LLM judge)
license_declared— is a license declared in the public model card / tags?task_declared— is the pipeline/task declared?model_card_present— does a public model card exist?
Guardrails (bound — do not relax)
- Public artifacts only (HF public model-info endpoint) — hiQ/Van Buren footing. Never scans a private API.
- Measurement, not certification — this is a verified measurement signal, not an ISO-17024/17065 accredited certificate of conformity. Report it as such.
- To sign the card, add
--sign(requires the signing key on the signing node); off the node it stays UNSIGNED and is labelled so — never a fake signature.
Verify a signed card
csoai verify --record card.json # Ed25519, offline, against the published key
Canonical grader: the csoai package (csoai check). This Skill is a thin discovery
rail over it, not a second implementation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 46 lines · 100 tokens per session scan A 7b6b61c9105c
eu-ai-act-art50-check is a skill published in the GitHub repository CSOAI-ORG/csoai-static-deploy2 (0 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 558 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
complyedge-eu-ai-act-runtime-deny
Runtime deny for EU AI Act Article 5 and Article 50 on this prompt or output via ComplyEdge TrustLint MCP. Use when the user wants agent I/O compliance enforcement, not system classification, FRIA forms, or C2PA watermarking.
eu-ai-act-compliance-mcp
EU AI Act compliance checking and risk classification. Automated compliance validation for high-risk AI systems with Article 11 technical documentation generation.
compliance-scan
Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.
interpret-results
Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.
ai-act-compliance
Use when the user asks about EU AI Act (Regulation 2024/1689) compliance — classifying an AI system's risk tier (art. 5 prohibited / art. 6 + Annex III high-risk / art. 50 limited / minimal), evaluating conformity for high-risk AI (art. 8–17, 26–27), drafting Annex IV technical documentation, conducting a Fundamental…
ai-act-assessment
Run a structured EU AI Act risk assessment for an AI system using the AI Act Companion engine. Use when the user wants to assess, classify or document an AI system under the EU AI Act / NIST AI RMF - e.g. determine its risk tier, or generate a risk assessment, DPIA, or bias-audit checklist.