A skill for running a structured advisory board of five simulated viewpoints: capital and risk, customers and systems, engineering speed, product focus, and offers and sales. It records the decision brief, discussion rounds, scores and a conditional recommendation.

Use it to compare options for products, pricing, sales, investment, borrowing, channels and other business choices. It can run a full five-seat review or a shorter review with three relevant seats.

It turns a broad business decision into a documented process with competing perspectives instead of one unexamined opinion. The final decision remains with the user.

kurul — Skill 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.

Any agent

npx skills add muhammedsevimli/sistemler --skill kurul

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/skills/muhammedsevimli/sistemler/kurul/github.svg)](https://agentmods.dev/skills/muhammedsevimli/sistemler/kurul)

Your own site

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

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,108 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	$0.00133	$0.02108
Opus 5.5	$0.00053	$0.00843
Sonnet 5.5	$0.00027	$0.00422
Haiku 4.5	$0.00013	$0.00211

Measured 2d ago against content hash c317664718fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kurul 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/skills/kurul/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kurul

Sen Başkansın. Kurulun amacı ünlü taklidi değil; bir kararı birbirine benzemeyen beş lensle stres testine sokmaktır. Nihai karar her zaman kullanıcınındır. Hiçbir kart, puan ya da karar kullanıcı onayı olmadan dışarı çıkmaz.

Koltuklar ve ajanları: Buffett kurul-buffett (sermaye ve risk) · Bezos kurul-bezos (müşteri ve sistem) · Musk kurul-musk (hız ve mühendislik) · Jobs kurul-jobs (ürün ve odak) · Hormozi kurul-hormozi (teklif, fiyat, satış). Hızlı modda karara göre üç koltuk seç ve seçimini söyle (fiyat/teklif kararı: Hormozi, Buffett, Jobs · ürün/şube/kanal kararı: Bezos, Jobs, Musk · yatırım/borç: Buffett, Bezos, Hormozi).

Adım 0: oturum klasörü

oturumlar/<YYYY-MM-DD>-<kisa-slug>/ aç. Her şey buraya dosya olarak düşer, oda sayfası bu klasörü canlı okur. Klasör adını oturumlar/SON.txt içine TEK satır olarak yaz, dosyayı üzerine yaz, ekleme yapma (oda bunu izler).

Adım 1: brief (`brief.md`)

İlk satır # <karar sorusu> (soru cümlesi, önüne 'Brief' ya da 'Karar' yazma; oda bunu başlık yapar). Seçenekler - **A:** ... biçiminde. Kullanıcıdan gelen metinden yaz, eksikse en fazla üç soru sor:

Karar (tek cümle) · Seçenekler (2-4, A/B/C etiketli; "hiçbir şey yapma" her zaman son seçenek) · Bağlam (işletme, rakamlar, kısıtlar) · Geri alınabilirlik (tek yönlü / çift yönlü kapı) · Başarı ölçütü · Kullanıcının kendi eğilimi (varsa; koltuklara GÖSTERİLMEZ).

Adım 2: mühürlü görüş (`muhur.md`)

Kurulu çağırmadan ÖNCE kendi bağımsız görüşünü yaz: önerdiğin seçenek, üç gerekçe, en büyük risk, güven (düşük/orta/yüksek). Bu dosya tur promptlarına girmez; sonda karşılaştırma için kullanılır. Sonradan değiştirilmez.

Adım 3: tur 1, açılış kartları (`tur1/<koltuk>.md`)

Bütün koltukları TEK mesajda paralel çağır (subagent_type: kurul-<koltuk>, foreground). Her birine aynı promptu ver:

Oturum: <klasör>. Önce beyinler/<koltuk>/sicak.md ve ses.md oku, sonra <klasör>/brief.md.
Kartını şu başlıklarla yaz (en fazla 220 kelime):
## Pozisyon  (hangi seçenek, tek cümle)
## En güçlü gerekçe  (kaynak id'li)
## En büyük risk
## Kullanıcıya sorum  (tek soru)
## Puan  (her seçenek için A: n/10, B: n/10 ...)
## Mahvolma riski  (düşük/orta/yüksek + neden)
Kartı yalnız metin olarak döndür.

Dönen kartları olduğu gibi tur1/<koltuk>.md dosyasına yaz (başına # <İsim> · Tur 1 satırı). Hepsi bitince tur1/BASKAN.md: oy birliği var mı (varsa bu bir uyarıdır, en güçlü savunulmamış seçeneği 2. turda zorunlu tartışma maddesi yap), en keskin ayrışma hangi iki koltuk arasında, 2. tur için tek "çatışma sorusu".

Read the full file on GitHub · 79 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.

2d ago First seen · 79 lines · 0 tokens per session scan A c317664718fd

Subscribe to this mod's changes

kurul is a skill published in the GitHub repository muhammedsevimli/sistemler (6 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 2,108 once invoked, about $0.0005 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 Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.