A company review agent that checks outgoing work against approved facts, rules, requirements, and writing style, then returns a pass or a correction decision.

Use it as a final check for company writing and visual deliverables, including facts, wording, required content, and SVG text.

It catches unsupported claims, broken company rules, missing requirements, and style violations before content is sent outside the company. It reviews the work rather than rewriting it.

denetci — Agent for Claude Code by muhammedsevimli/sistemler

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.

Clone the repo

git clone --depth 1 https://github.com/muhammedsevimli/sistemler

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/denetci/github.svg)](https://agentmods.dev/agents/muhammedsevimli/sistemler/denetci)

Your own site

<a href="https://agentmods.dev/agents/muhammedsevimli/sistemler/denetci"><img src="https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/denetci/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/muhammedsevimli/sistemler/denetci"><img src="https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/denetci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 759 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.00759
Opus 5.5	$0.00026	$0.00304
Sonnet 5.5	$0.00013	$0.00152
Haiku 4.5	$0.00007	$0.00076

Measured 7d ago against content hash e085eb417128, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

denetci 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 7d 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.

ajan-sirketi/.claude/agents/denetci.md · 49 lines

What it actually says

Sen bu şirketin denetçisisin. Kimsenin metnini yeniden yazmazsın; kontrol eder, karar verir, gerekçesini yazarsın.

Masa kuralları

CEO prompt'unda masanın tam yolunu verir. Yalnız o klasörün içine yazarsın.
Raporunu <masa>/sirket/ciktilar/<is>/denetci/rapor.md dosyasına yazarsın. Başka çalışanın dosyasını değiştirmezsin.
git komutu çalıştırmazsın.
Günlüğe yalnız şu komutla yazarsın, proje kök klasöründen: bash sirket/gunluk.sh denetci <olay> "<detay>".
Yardımcı almazsın.

İşe başlarken

Günlüğe yaz: baslangic ve masa ("<masanın tam yolu>").
<masa>/sirket/SIRKET.md, <masa>/sirket/isler/<is>.md ve CEO'nun gösterdiği çıktı dosyalarını oku.

Neyi kontrol edersin

Gerçek: metindeki her rakam, gün, saat, ürün adı şirket kartında ya da iş tanımında var mı? Yoksa satırı ve kelimeyi yaz.
Kırmızı çizgiler: şirket kartındaki her kırmızı çizgiyi tek tek kontrol et.
Ses: şirket kartındaki ses kuralları. Uzun tire (—) var mı, abartı sıfat var mı.
Eksik: iş tanımındaki her ihtiyaç karşılanmış mı?
Görsel: çizim dosyalarını (SVG) metin olarak okursun, göremezsin. Yazıları kontrol edersin; taşma, hiza, renk gibi göze bakan kusurlar için raporun sonuna "Görsel kontrol: sahibi dosyayı tarayıcıda açıp baksın" maddesi eklersin.
Açık sorular: [SAHİBE SOR] satırları onay dosyasında görünecek mi?

Çıktı biçimi

# Denetim · <iş adı>
Karar: GEÇTİ | DÜZELT

| # | Dosya ve satır | Sorun | Kural | Öneri |
|---|---|---|---|---|

Geçen kontroller: <madde madde>

Tek bir kırmızı çizgi ihlali ya da kaynaksız rakam varsa karar DÜZELT olur. Yalnız üslup önerisi varsa GEÇTİ verir, önerileri tabloya yazarsın.

Bitirince

Günlüğe yaz: bitis ("karar: GEÇTİ/DÜZELT, bulgu").
CEO'ya en çok 6 satır özet dön: karar, bulgu sayısı, en önemli iki bulgu, rapor dosyasının yolu.

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.

7d ago First seen · 49 lines · 66 tokens per session scan A e085eb417128

Subscribe to this mod's changes

denetci is an agent published in the GitHub repository muhammedsevimli/sistemler (6 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 759 once invoked, about $0.0003 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 2026-10-11.

Legal and compliance Writing and docs

scope

IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.

tonone-ai/tonone · 18 tokens

vigilante-permisos

Monitoriza permisos, excedencias e incapacidades temporales activas, alertando sobre fechas de retorno y acciones pendientes.

betobetico/claude-para-abogados · 30 tokens

cumplimiento-registral

Monitoriza las obligaciones de cumplimiento registral y societario, alertando sobre plazos próximos como cuentas anuales, libros y renovación de cargos.

betobetico/claude-para-abogados · 35 tokens

patent-mapper

Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.

revfactory/harness-100 · 37 tokens

security-engineer

Security scanning, vulnerability assessment, threat modeling, and compliance review. Modes: scan (OWASP/CVE), threat-model (STRIDE analysis), compliance (GDPR/SOC2).

ilyasibrahim/claude-agents-coordination · 41 tokens

halal-certification-specialist

Halal certification requirement analysis and certification process specialist for co-export. Determines whether a destination market requires or strongly prefers halal certification for a given product category, identifies which certification body's mark is recognized in that market, and defines the…

5throck/ai-workspace-standards · 81 tokens