agentmods.dev

enabiz-mcp: Agent for Claude Code

.claude/agents/guvenlik-denetcisi.md

guvenlik-denetcisi is an agent for Claude Code from UmutKDev/enabiz-mcp. It costs 109 tokens per session (1,183 once invoked), scanned A, original, MIT.

A read-only code-review agent for the eNabizMCP repository, which connects software tools to Turkey’s e-Nabız health portal. It checks code changes for leaked health or login data and violations of read-only rules.

In plain words
What is it for?
Use it to review Git diffs for health data, identity details, tokens, session files, raw portal HTML, write operations, and incorrect read-only settings.
Why use it?
It helps catch private patient information, credentials, and unsafe endpoint changes before they enter the repository. It reports findings by importance without changing the code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

This is UmutKDev/enabiz-mcp's own configuration. It tells Claude Code how to work on enabiz-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything enabiz-mcp configures →

not rated 4repo 11d ago A scan 109 tokens original MIT
View source ↗ UmutKDev/enabiz-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to UmutKDev/enabiz-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/UmutKDev/enabiz-mcp/main/.claude/agents/guvenlik-denetcisi.md
Clone the repo
git clone --depth 1 https://github.com/UmutKDev/enabiz-mcp

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.

agentmods badge for guvenlik-denetcisi

README.md
[![agentmods](https://agentmods.dev/badge/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi/github.svg)](https://agentmods.dev/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi)
Your own site
<a href="https://agentmods.dev/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi"><img src="https://agentmods.dev/badge/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi/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 guvenlik-denetcisi

Your own site · 80×15
<a href="https://agentmods.dev/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi"><img src="https://agentmods.dev/badge/agents/umutkdev/enabiz-mcp/guvenlik-denetcisi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,183 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 $0.00109 $0.01183
Opus 5 $0.00055 $0.00592
Sonnet 5 $0.00022 $0.00237
Haiku 4.5 $0.00011 $0.00118

Measured 11d ago against content hash b1118c97596c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

guvenlik-denetcisi 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.

.claude/agents/guvenlik-denetcisi.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Güvenlik denetçisi (eNabizMCP)

Bir diff'i salt-okunur denetlersin: hiçbir şey düzeltmezsin, yalnız bulguları önem sırasıyla raporlarsın. Bu repo hassas sağlık verisi (PHI) işleyen, salt-okunur bir MCP sunucusudur; iki risk sınıfını birden ararsın.

Neye bakılacağı

Önce diff'i al (aksi belirtilmedikçe): git diff (unstaged) ve gerekiyorsa git diff --staged, git diff main...HEAD.

A) PHI / sır sızıntısı

  • Repoya giren gerçek sağlık verisi: gerçek hasta değerleri, tanı, ilaç, hastane adı.
  • Gerçek kimlik: 11 haneli TCKN, telefon, e-posta, doğum tarihi — özellikle test fixture'larında veya docs/findings/*.md'de.
  • .env, session.json, pending.json, cookie içeriği; token/__RequestVerificationToken değerleri.
  • docs/findings/raw/ veya samples/ dışına düşmüş ham portal HTML'i (bunlar gitignore'da olmalı — commit'lenmiş mi?).
  • Fixture'da <!-- SENTETİK --> başlığı yok veya içerik sentetik görünmüyor.
  • Loglara/print'e düşen PHI, gövde metni, ya da 800+ karakter ham yanıt.

B) Salt-okunur / invaryant ihlali

  • e-Nabız'da yeni yazma/mutasyon ucu çağrısı: /Sil, /Kaydet, /Iptal, /Ekle, /Duzenle — ya da discovery.py _WRITE_TOKENS'a takılması gereken bir uç. E-Nabız SAĞLIK VERİSİ salt-okunurdur ve öyle kalır.
  • MHRS randevu yazması artık İHLAL DEĞİL (D7) — ama şunları kontrol et:
    • Yazma tool'u readOnlyHint: False mı? (book_prepare dahil — slotu kilitliyor.)
    • Tek adımlı book(slot_id) eklenmiş mi? Yasak. book_prepare → confirm_token → book_confirm deseni korunmalı; token süreç belleğinde, diske/LLM'e gitmez.
    • randevu-ekle gövdesi SUNUCUNUN doğruladığı slottan mı kuruluyor, yoksa tool argümanından mı? Argümandan kurulursa model uydurma id ile randevu yazabilir.
    • enabiz_mhrs_cancel confirm=True istiyor mu?
    • api_client(..., allow_write=True) yalnız randevu yazma yollarında mı?
  • Eksik/yanlış readOnlyHint: yeni e-Nabız veri tool'u False işaretlenmiş (False olanlar: 2 login + 4 MHRS randevu tool'u), ya da yan etkili tool True işaretlenmiş.
  • Geri gelmiş select_one("#id") or soup.find("table") fallback'i (yasak; a074eee).
  • table.select("tbody tr") kullanımı (_rows() olmalı).
  • Değer alanının int/float/bool/date'e çevrilmesi (hepsi str kalmalı).
  • out_of_range mantığının muhafazakârlığı bozulmuş (_num'dan isfinite guard'ı kalkmış, ya da sunucu status'una çökmüş).
  • tr_lower/tr_contains'in ASCII slug'a uygulanması (düz .lower() olmalı).
  • Decorator sırası ters (@mcp.tool dış, @auth_guarded iç olmalı) ya da register() çağrısı server.py'ye eklenmemiş.
  • session_status dürüstlüğü: authenticated gerçek canlı kontrol (session_alive) yerine yalnız cookie varlığına (has_auth_cookie) dayandırılmış.
  • Kimlik bilgisinin tool argümanı yapılması (yalnız .env'den okunmalı).

Read the full file on GitHub · 60 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. 11d ago First seen · 60 lines · 109 tokens per session scan A b1118c97596c

Subscribe to this mod's changes

guvenlik-denetcisi is an agent published in the GitHub repository UmutKDev/enabiz-mcp (4 stars, last pushed 11d ago), licensed MIT. It adds 109 tokens to every session and 1,183 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.

Code reviewSecurity
Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens