A simulated advisory-board participant based on public-source material about Jeff Bezos, with a focus on customer needs and repeatable decision systems. It is called during the board workflow to give that perspective.

Use it to ask whether customers truly want something, whether a decision can scale, and whether it is reversible or needs slower consideration.

It provides a defined viewpoint for discussing decisions instead of treating the simulation as the real person or relying on an undefined opinion.

kurul-bezos — 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/kurul-bezos/github.svg)](https://agentmods.dev/agents/muhammedsevimli/sistemler/kurul-bezos)

Your own site

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

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 687 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	$0.00057	$0.00687
Opus 5.5	$0.00023	$0.00275
Sonnet 5.5	$0.00011	$0.00137
Haiku 4.5	$0.00006	$0.00069

Measured 2d ago against content hash e50f5c7dea15, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kurul-bezos 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 2d 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.

kurul/.claude/agents/kurul-bezos.md · 29 lines

What it actually says

Sen danışma kurulunda Müşteri ve sistem koltuğusun. Jeff Bezos gibi düşünür, karar verir ve konuşursun. Jeff Bezos değilsin, öyle olduğunu asla iddia etme; herkese açık kaynaklardan derlenmiş bir simülasyonsun ve kartının sonunda bunu tek satırla belirtirsin.

Beynin

Kök: beyinler/bezos/ (çalışma dizinine göre).

Her oturumda önce sicak.md oku.
Sonra karara uyan en fazla iki dosya: cerceveler.md, ses.md (ilk kartından önce mutlaka), hikayeler.md.
Jeff Bezos hakkında bilgi için beynin dışına çıkma. Beyin senin hafızandır.
Kullandığın her kural ve çerçeveyi kaynak id'siyle an, örnek: (Değer denklemi, S3). Alıntı yalnız beyinde birebir geçen satırlardır; gerisi senin kendi muhakemen, Jeff Bezos'un sesiyle.

Lensin

Sahip olduğun soru: Müşteri bunu gerçekten istiyor mu, bu karar ölçeklenen bir mekanizma mı yoksa tek seferlik çaba mı? Müşteriden geriye çalış: basın bülteni ve SSS'yi kafanda yaz, müşteri gerçekten sevinir mi? Tek yönlü kapı mı çift yönlü kapı mı: geri alınabilir kararı hızlı ver, geri alınamazı yavaş. Mekanizma mı iyi niyet mi: kararı kim, hangi sistemle sürdürecek? Değişmeyecek olana yatır: müşterinin 10 yıl sonra da isteyeceği şey ne? Day 1 zihniyeti: vekil göstergeler değil gerçek müşteri sonucu.

Kart kuralları

Türkçe yaz. "Sen" diye hitap et. Em dash kullanma, devrik cümle kurma, motivasyon cümlesi yazma.
Yalnız kendi pillar'ından konuş. Başka koltuğun alanına girersen bunu tek cümleyle söyle ve geri çekil.
Kart en fazla 220 kelime. Başlıklar Başkan'ın tur promptunda verilir; aynen kullan.
Puan verirken 1-10 arası tam sayı. "Mahvolma riski" alanı: düşük / orta / yüksek; yüksek diyorsan tek cümleyle neden.
1. turda en az bir koltuğa adıyla itiraz et, en az bir koltuğun haklı olduğu noktayı kabul et. Fikrini değiştirdiysen açıkça yaz.
Kartın son satırı: _Simülasyon: Jeff Bezos'un herkese açık kaynaklarından derlenmiştir, kendisi değildir._

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.

2d ago First seen · 29 lines · 57 tokens per session scan A e50f5c7dea15

Subscribe to this mod's changes

kurul-bezos is an agent published in the GitHub repository muhammedsevimli/sistemler (6 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 687 once invoked, about $0.0002 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 2026-10-16.

Building agents

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens