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 esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri --skill dilekce-cracgit clone --depth 1 https://github.com/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleriWrote 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/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/dilekce-crac)<a href="https://agentmods.dev/skills/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/dilekce-crac"><img src="https://agentmods.dev/badge/skills/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/dilekce-crac/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/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/dilekce-crac"><img src="https://agentmods.dev/badge/skills/esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri/dilekce-crac.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 | $0.00173 | $0.01327 |
| Opus 5.5 | $0.00069 | $0.00531 |
| Sonnet 5.5 | $0.00035 | $0.00265 |
| Haiku 4.5 | $0.00017 | $0.00133 |
Grade A, and why
dilekce-crac 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRAC ile Dilekçe Oluşturma
CRAC, CREAC'in sadeleştirilmiş hâlidir: ayrı bir Explanation/açıklama katmanı yoktur. Sonucu baştan koyar, kuralı anar, somut olaya uygular ve sonucu yineler. Kuralın tartışmasız olduğu, hızlı ve doğrudan ifade gerektiren dilekçelerde; iddianın daha ilk cümlede net görünmesini sağlar.
Ne zaman kullanılır
- Uygulanacak kural tartışmasız; uzun bir kural açıklamasına (Explanation) gerek yok.
- Dilekçenin kısa, doğrudan ve sonuç-merkezli olması isteniyor.
- Ara dilekçeler, beyan dilekçeleri, basit talepler ve hızlı yanıtlar.
- Dava, cevap, replik, düplik veya ceza savunması — tür fark etmez.
CRAC mantığı
- C — Sonuç (Conclusion): Varılması istenen sonucu/iddiayı baştan, tek cümlede net koy.
- R — Kural (Rule): Uygulanacak mevzuat/içtihat/ilke (kısa; ayrı açıklama katmanı yok).
- A — Uygulama (Application): Kuralı somut olaya tatbik et (işin kalbi).
- C — Sonuç (Conclusion): Baştaki sonucu pekiştirerek talebe bağla.
Çalışma akışı
- Dilekçe türünü belirle (dava/cevap/replik/düplik/savunma) —
references/bicim-ve-cikti.md. - Bilgileri topla: mahkeme ve dosya no, taraflar, konu, talepler, vakıalar, deliller.
Eksikleri
AskUserQuestionveya kısa sorularla tamamla. Dava dosyası verildiyse oku:.udf→udf-cli udf2md; çok sayfalı.tiff/.tif→ sayfalara böl, tek tek oku; PDF/foto/metin → doğrudan oku. - CRAC iskeletini kur — adım tanımları ve eşleme tablosu için
references/cerceve-yapisi.md. - Gövdeyi yaz: İddiayı baştan koy; AÇIKLAMALAR'ı
C → R → A → Cakışıyla kur. Gereksiz açıklama katmanı ekleme; her hukuki mesele için ayrı, kısa bir CRAC bloğu yeterlidir. - Çıktıyı üret (docx/html/udf/pdf) —
references/bicim-ve-cikti.md. - Doğrula ve sun.
CRAC adımlarının dilekçe bölümlerine eşlemesi
| CRAC adımı | Dilekçe bölümü | İçerik |
|---|---|---|
| Sonuç (baştaki) | KONU + AÇIKLAMALAR başı | Baştan konulan iddia/sonuç cümlesi |
| Kural | HUKUKİ NEDENLER (+ gövdede atıf) | Dayanak mevzuat/içtihat/ilke |
| Uygulama | AÇIKLAMALAR (irdeleme) | Kuralın somut olaya tatbiki |
| Sonuç (sondaki) | NETİCE VE TALEP | Baştaki sonucun talebe bağlanması |
What ships with it
2 files 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.
- 1mo ago First seen · 76 lines · 173 tokens per session scan A 7cdd2f49aa7b
dilekce-crac is a skill published in the GitHub repository esaterbiltavus/yapay-zeka-turkce-dilekce-skilleri (16 stars, last pushed 4mo ago), licensed MIT. It adds 173 tokens to every session and 1,327 once invoked, about $0.0007 per session on Opus 5.5. 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.
Other skills, from other repositories
kr-patent-consistency-check
A Korean patent-document checker for comparing a patent specification, drawings, and claims—the sections that describe an invention and define its legal protection.
kr-patent-spec-drafting
A workflow for writing the main text of a Korean patent specification from draft claims and invention materials, following Korean Patent Office filing structure.
kr-patent-claim1-drafting
A Korean patent-writing procedure for drafting claim 1, the main independent claim in a patent. It turns a paper or invention description into a method claim using a fixed structure and requires approval at key decisions.
kr-patent-dependent-claim-drafting
A Korean patent-writing tool for creating dependent claims, system claims, program claims, and additional independent claims from a paper or invention description and an approved first claim.
kr-patent-full-workflow
A coordinator for writing a Korean patent specification from start to finish. It guides the work through invention interviews, claim preparation, technical details, consistency checks, and final DOCX output.
patent-block-diagram
A workflow that turns a natural-language description into an editable `.pbd` patent block diagram, renders it in the diagram editor, checks the image, and exports a PNG.