agentmods.dev

enabiz-mcp: Instructions file for Claude Code

CLAUDE.md

enabiz-mcp CLAUDE.md is an instructions file for Claude Code from UmutKDev/enabiz-mcp. It costs 2,383 tokens per session, scanned A, original, MIT.

Project instructions for enabiz-mcp, a local read-only server that lets a language model access personal Turkish health-system data through a standard connection.

In plain words
What is it for?
Guiding development of the server's tools, data parsers, endpoint discovery, and version updates.
Why use it?
They document safety rules for sensitive health data, including which systems must remain read-only and where appointment actions require confirmation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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 6d ago A scan 2,383 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.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 enabiz-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/umutkdev/enabiz-mcp/claude-md.svg)](https://agentmods.dev/instructions/umutkdev/enabiz-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/umutkdev/enabiz-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/umutkdev/enabiz-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,383 This file is loaded in full into every session.
When invoked 2,383 The same file — it is already loaded in full.
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 $0.02383 $0.02383
Opus 5 $0.01192 $0.01192
Sonnet 5 $0.00477 $0.00477
Haiku 4.5 $0.00238 $0.00238

Measured 7d ago against content hash 4f6750837479, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

enabiz-mcp CLAUDE.md 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.

CLAUDE.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — eNabizMCP

E-Nabız (T.C. Sağlık Bakanlığı Kişisel Sağlık Sistemi) verisine bir LLM üzerinden erişmek için yerel, salt-okunur MCP sunucusu. Hassas sağlık verisi (PHI) işler; yalnız stdio üzerinden çalışır.

Bu dosya her zaman geçerli olanı tutar. Adım-adım iş akışları skill'lerdedir (.claude/skills/): yeni tool, yeni parser, endpoint keşfi, sürüm güncelleme.

Değişmez invaryantlar (bunları asla ihlal etme)

  1. Salt-okunur — sisteme göre. İki sistem var, kural ayrışır (gerekçe: decisions.md D7).
    • E-Nabız (KSS) sağlık verisi: SALT-OKUNUR. Hiçbir tool /Sil, /Kaydet, /Iptal gibi bir yazma ucu çağırmaz. Test edilen invaryant: e-Nabız keşif tarayıcısı bir yazma ucuna dokunursa suite kasten patlar — tests/test_discover_scan.py:44-45. discovery.py:56-59 denylist'i (RandevuAl/ManuelRandevu dahil) aynen durur, gevşetilmez. MHRS sınıflayıcısında ad kapısını yalnız _VERIFIED_READS ezer: canlıda çağrılıp yazmadığı ÖLÇÜLMÜŞ uçlar (ör. ayni-hekimden-randevu-al randevu almaz, kriter döndürür). Ölçüm olmadan giriş YOK.
    • MHRS (randevu): YAZMA AÇIK. Randevu alma/iptal prd.mhrs.gov.tr API'sinde, readOnlyHint: False ve iki-adımlı onay ile yapılır: book_prepare slotu doğrulayıp confirm_token döner, book_confirm randevuyu alır. Tek adımlı bir book(slot_id) YAZMA — LLM'in uydurduğu slot id kullanıcıya 15 günlük gerçek branş yasağı yazdırır. randevu-ekle gövdesi tool argümanından DEĞİL, sunucunun doğruladığı slottan kurulur. api_client(..., allow_write=True) açık niyet beyanıdır. book_prepare randevu almaz ama readOnlyHint: True DEĞİL — MHRS o çağrıda slotu kilitliyor; vazgeçince book_cancel_prepare bırakır.
    • Durum değiştiren tool'lar: enabiz_login_start (SMS), enabiz_login_verify (oturum) + MHRS randevu yazma tool'ları. Başka hiçbiri.
  2. Sessiz yanlış-eşleme, boş sonuçtan KÖTÜDÜR. Beklenen tablo id'si yoksa [] dön. Asla select_one("#id") or soup.find("table") fallback'i ekleme — bu tam olarak a074eee'de 15 parser'dan silinen sessiz-bozulma hatası (eksik id'de sayfanın ilk nav/layout tablosunu sağlık modeline eşliyordu). Kilitleyen test: tests/test_parser_robustness.py:28-39.
  3. PHI, LLM bağlamına girmez. İndirme tool'ları içerik değil {saved_path, byte_size, sha256, content_type} döner (src/enabiz_mcp/downloads.py:31-36). Kimlik yalnız .env'den (ENABIZ_TCKIMLIK/ENABIZ_SIFRE), tool argümanı DEĞİL — LLM bağlamına hiç girmez. Oturum ve indirilen dosyalar chmod 0o600.
  4. Güvenlik kontrolleri atlatılmaz. reCAPTCHA çözülmez, SMS OTP kaldırılmaz/kırılmaz; kod her zaman kullanıcının kayıtlı telefonuna gider, giriş insan-döngüdedir.
  5. PHI repoya girmez. Testler ağsız, sentetik fixture ile çalışır. Ham portal yanıtları (docs/findings/raw/), .env, oturum/cookie dosyaları gitignore'dadır; commit'lenen bulgu .md'lerine gerçek değer yazılmaz.

Read the full file on GitHub · 112 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. 7d ago First seen · 112 lines · 2,383 tokens per session scan A 4f6750837479

Subscribe to this mod's changes

enabiz-mcp CLAUDE.md is an instructions file published in the GitHub repository UmutKDev/enabiz-mcp (4 stars, last pushed 6d ago), licensed MIT. It adds 2,383 tokens to every session, about $0.0119 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens