agentmods.dev

politika-fark-takibi

politika-fark-takibi is a skill for Claude Code from kapital-legal/claude-for-tr-legal. It costs 125 tokens per session (1,891 once invoked), scanned A, original, Apache-2.0.

A Turkish-language compliance skill that compares a company's KVKK privacy policy or internal procedure with privacy-board decisions and current regulations supplied by the user. KVKK is Turkey's personal-data protection law.

In plain words
What is it for?
Use it to compare privacy policies, disclosure notices, retention rules, employee-data procedures, breach plans, or international-transfer clauses with supplied source material.
Why use it?
It highlights where the company's policy has fallen behind relevant decisions or legal changes and where revisions may be needed.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the kvkk-uyum-tr plugin — 8 skills shipped together

not rated 9repo 3mo ago A scan 125 tokens original Apache-2.0

Good fit Use it to compare privacy policies, disclosure notices, retention rules, employee-data procedures, breach plans, or international-transfer clauses with supplied source material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi
View source ↗ kapital-legal/claude-for-tr-legal
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 kapital-legal/claude-for-tr-legal --skill politika-fark-takibi
Clone the repo
git clone --depth 1 https://github.com/kapital-legal/claude-for-tr-legal

Made for: Claude Code.

Or install kvkk-uyum-tr, the plugin that ships this one along with the rest of its 8 skills.

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 politika-fark-takibi

README.md
[![agentmods](https://agentmods.dev/badge/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi/github.svg)](https://agentmods.dev/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi)
Your own site
<a href="https://agentmods.dev/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi"><img src="https://agentmods.dev/badge/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi/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 politika-fark-takibi

Your own site · 80×15
<a href="https://agentmods.dev/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi"><img src="https://agentmods.dev/badge/skills/kapital-legal/claude-for-tr-legal/politika-fark-takibi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,891 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 $0.00125 $0.01891
Opus 5 $0.00063 $0.00945
Sonnet 5 $0.00025 $0.00378
Haiku 4.5 $0.00013 $0.00189

Measured 12d ago against content hash 85e56b2e9e86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

politika-fark-takibi 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.

kvkk-uyum-tr/skills/politika-fark-takibi/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kvkk-uyum-tr:politika-fark-takibi

Bu skill otomatik karar tarama yapmaz. Kullanıcı incelenecek kararların URL/metnini sağlamalı, plugin politikayla karşılaştırarak fark üretir.

Cold-start kontrolü

Profil yoksa interview'a yönlendir.

İş Akışı

1. Politika dosyasını oku

Read(politika-dosyası)

Tipik politika dokümanları:

  • Şirket içi KVKK Politikası
  • Aydınlatma Metni (web/sözleşme)
  • Veri Saklama ve İmha Politikası
  • Erişim Yönetimi Prosedürü
  • İhlal Müdahale Planı
  • Çalışan Veri İşleme Politikası

Politikadaki ana konuları çıkar:

  • Hangi veri kategorilerini işliyor?
  • Hangi hukuki sebepleri dayanak gösteriyor?
  • Saklama süreleri belirtilmiş mi?
  • Çalışan/müşteri/ziyaretçi izlemeleri nasıl tarif ediliyor?
  • İhlal müdahale süreci var mı?
  • Yurt dışı aktarım maddesi var mı?

2. Karşılaştırılacak kararları al

Kullanıcı şu üç yoldan biriyle sağlar:

  • URL listesi: https://www.kvkk.gov.tr/Icerik/<XXXX>/<YYYY-NN>, https://... (örnek format — kullanıcının kvkk.gov.tr'den getirdiği gerçek URL'lerle değiştir) Plugin WebFetch ile her birini çeker.
  • Yapıştırılmış metinler: Kullanıcı 3-5 karar metnini bir bütün olarak yapıştırır.
  • Dosya yolu: Kullanıcı kararları topladığı bir Markdown/PDF dosyası verir.

Eğer kullanıcı kararları sağlamamış ise, plugin önerir:

Politika fark analizi için kararları senin sağlaman gerek. İki seçenek var:

  1. kvkk.gov.tr → Karar Özetleri sayfasında son 12 ayın kararlarına bak, ilgili olanların URL'ini buraya yapıştır.
  2. Eğer "şu konuda son ne çıkmış?" sorun varsa, önce /kvkk-uyum-tr:karar-analizi ile spesifik bir karar çek; bu skill ile daha sonra fark karşılaştırması yap.

Plugin kendisi karar veritabanına bağlanmaz — bu, müvekkil mahremiyeti ve TBB Meslek Kuralları çerçevesinde bilinçli bir tasarım kararıdır.

3. Fark analizi (gap analysis)

Her politika konusu için:

Politika Maddesi Mevcut Durum Karar Yorumu Sapma? Aksiyon
Çalışan e-posta izleme "Şirket politikamızca izlenebilir" Kullanıcının verdiği karar: aydınlatma + makul şüphe + sınırlı amaç gerekli ⚠️ Sapma Politikaya aydınlatma + amaç sınırı ekle
Saklama süresi "Ticari ihtiyaç süresince" [İlgili karar yorumu] ⚠️ Belirsiz Süreleri tablo halinde yaz
Yurt dışı (ABD) aktarım "Açık rıza ile" [Güncel karar yorumu] ⚠️ Kritik KVKK m.9 standart sözleşme imzala
... ... ... ... ...

Read the full file on GitHub · 148 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 · 148 lines · 125 tokens per session scan A 85e56b2e9e86

Subscribe to this mod's changes

politika-fark-takibi is a skill published in the GitHub repository kapital-legal/claude-for-tr-legal (9 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,891 once invoked, about $0.0006 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.

Legal and compliance
Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens