vendor-ai-review

vendor-ai-review is a skill for Claude Code from ZekaiSuni/claude-for-legal-turkish. It costs 84 tokens per session (1,251 once invoked), scanned A, original, Apache-2.0.

A checklist for reviewing how a supplier's software or services use artificial intelligence, customer data, and intellectual property. It examines terms such as model training, telemetry, Copilot, and data inputs and outputs under Turkish legal considerations.

In plain words
What is it for?
Use it to find AI-related clauses in supplier terms, check training and data-use permissions, assess KVKK, FSEK, and TTK concerns, draft suggested edits, and flag matters for privacy or data-protection review.
Why use it?
It helps reveal whether a supplier may use company data to train models or create risks involving personal data, trade secrets, or ownership of work.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ai-governance-legal plugin — 10 skills, 3 MCP servers shipped together

Good fit Use it to find AI-related clauses in supplier terms, check training and data-use permissions, assess KVKK, FSEK, and TTK concerns, draft suggested edits, and flag matters for privacy or data-protection review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review
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.

Any agent
npx skills add ZekaiSuni/claude-for-legal-turkish --skill vendor-ai-review
Clone the repo
git clone --depth 1 https://github.com/ZekaiSuni/claude-for-legal-turkish

Made for: Claude Code.

Or install ai-governance-legal, the plugin that ships this one along with the rest of its 10 skills, 3 MCP servers.

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 vendor-ai-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review/github.svg)](https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review)
Your own site
<a href="https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review"><img src="https://agentmods.dev/badge/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review/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.

agentmods 80×15 button for vendor-ai-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review"><img src="https://agentmods.dev/badge/skills/zekaisuni/claude-for-legal-turkish/vendor-ai-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00084 $0.01251
Opus 5 $0.00042 $0.00626
Sonnet 5 $0.00017 $0.00250
Haiku 4.5 $0.00008 $0.00125

Measured 12d ago against content hash c4f156abc562, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vendor-ai-review 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.

ai-governance-legal/skills/vendor-ai-review/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/vendor-ai-review (Tedarikçi AI / Copilot Sözleşme İncelemesi)

Amaç

Tedarikçilerin (özellikle SaaS hizmetlerinin) kullanım koşullarında (Terms of Service) yer alan AI ve Copilot şartlarını incelemek. Temel soru: "Müşteri (yani şirketimiz) olarak bu veriyle onların modelini eğitiyor muyuz?"

Bu skill, AI maddelerini KVKK, FSEK ve TTK (Ticari Sır) riski açısından inceler ve ilgili maddelerin redline (düzeltme) önerisini oluşturur.

İş Akışı

  1. Sözleşmeyi tara ve "Artificial Intelligence", "Machine Learning", "Model Training", "Data Usage", "Telemetry", "Copilot" veya "Output/Input" kelimelerini bul.
  2. Aşağıdaki Türkiye ve Enterprise Odaklı AI Kontrol Listesini (Checklist) uygula.
  3. Kırmızı çizgileri saptayıp, Hukuk Kuralları çerçevesinde (Opt-out vs. Opt-in) redline taslağını sun.
  4. Privacy/Data Protection birimine handoff yapılacak bir madde varsa raporla.

Türkiye Odaklı AI Kontrol Listesi

1. Model Eğitimi (Training & Machine Learning)

  • Sözleşme, tedarikçinin Customer Data'yı (Kişisel Veri, Loglar, Analitik Veriler dahil) kendi modellerini veya üçüncü parti (OpenAI vb.) modelleri eğitmek için kullanılmasına (training) izin veriyor mu?
  • Hedefimiz: SIFIR eğitim yetkisi (Zero training rights) veya mutlak "Opt-out" (eğitimden çıkış) hakkı vermek. Redline hedefi: "Tedarikçi, Müşteri Verilerini ve Müşteri Çıktılarını hiçbir dil modelini (LLM) veya yapay zeka aracını eğitmek amacıyla YARARLANAMAZ."

2. Girdiler ve Çıktılar (Inputs and Outputs)

  • Prompt (Girdi) ve Output (Çıktı) kime ait?
  • FSEK ve Sözleşme Riski: Üretilen içeriğin/kodun mülkiyeti Müşteriye devrediliyor mu? Tedarikçi, bu çıktıları başka müşterilere gösterme veya saklama hakkına sahip mi?
  • Hedefimiz: Çıktıların mülkiyetinin ve teliflerinin (FSEK uyarınca devredilebilen ekonomik haklar) münhasıran şirkete ait olması.

3. KVKK ve Yurt Dışı Veri Aktarımı (KVKK m.9)

  • Girdiğimiz Müşteri verileri, tedarikçi tarafından üçüncü taraf AI modellerine (örn. OpenAI API) aktarılıyor mu?
  • Eğer aktarılıyorsa bu tedarikçiler "Alt-Veri İşleyen" (Sub-processor) olarak listelenmiş mi?
  • Verinin işlendiği sunucular nerede (ABD, AB)? Özel Nitelikli Kişisel Veri aktarım kısıtı var mı?

Read the full file on GitHub · 71 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. 12d ago First seen · 71 lines · 84 tokens per session scan A c4f156abc562

Subscribe to this mod's changes

vendor-ai-review is a skill published in the GitHub repository ZekaiSuni/claude-for-legal-turkish (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,251 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

prowler-compliance

Creates, syncs, audits and manages Prowler compliance frameworks end-to-end. Covers the two supported JSON schemas (universal multi-provider and legacy per-provider), the SDK model tree (legacy attribute classes, universal ComplianceFramework, ConfigRequirements guardrails), output formatters (legacy per-framework +…

prowler-cloud/prowler · 227 tokens

policy

Define and enforce decision policies, compliance rules, and exceptions over Semantica graphs. Uses ContextGraph.checkdecisionrules/enforcedecisionpolicy and context.PolicyEngine.

semantica-agi/semantica · 36 tokens

801-regulations-eu-ai-act

Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance…

jabrena/plinth · 108 tokens

813-regulations-iso-42001

Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…

jabrena/plinth · 77 tokens

open-weights

Use when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping. Owns the license-class map (OSI-open versus custom-community versus non-commercial), the always-verify-the-model-card rule, size-to-VRAM…

ericrisco/rsc-harness · 146 tokens

ai-policy-generator

AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.

travisjneuman/.claude · 42 tokens