matematikci

matematikci is an agent for Claude Code from muhammedsevimli/sistemler. It costs 57 tokens per session (802 once invoked), scanned A, original, MIT.

A data-review role that tests competing explanations using only the numbers in a set of files. It shows calculations and marks claims as supported, contradicted, or undecidable.

In plain words
What is it for?
Use it to inspect datasets, compare theories, calculate derived values, and write evidence-based decisions for a discussion.
Why use it?
It prevents arguments from relying on guesses, outside averages, or missing evidence. It makes the numerical basis for each decision explicit.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to inspect datasets, compare theories, calculate derived values, and write evidence-based decisions for a discussion.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/muhammedsevimli/sistemler/matematikci
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.

agentmods badge for matematikci

README.md
[![agentmods](https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/matematikci/github.svg)](https://agentmods.dev/agents/muhammedsevimli/sistemler/matematikci)
Your own site
<a href="https://agentmods.dev/agents/muhammedsevimli/sistemler/matematikci"><img src="https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/matematikci/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 matematikci

Your own site · 80×15
<a href="https://agentmods.dev/agents/muhammedsevimli/sistemler/matematikci"><img src="https://agentmods.dev/badge/agents/muhammedsevimli/sistemler/matematikci.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 802 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 $0.00057 $0.00802
Opus 5.5 $0.00023 $0.00321
Sonnet 5.5 $0.00011 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 1mo ago against content hash 23e946b0b017, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

matematikci 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 1mo 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-takimi/.claude/agents/matematikci.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen bu tartışmanın hakemisin. Teorin yok ve olmayacak.

Araçların salt okunur. Dosya yazmazsın, kararını yanıt olarak dönersin, lider onu tartisma/ klasörüne yazar. Bu bilerek böyle: hakem tartışmanın çıktısına dokunamaz.

Değişmez kural

Yalnız veri/ klasöründeki dosyalarda yazan rakamla konuşursun. O klasörde olmayan hiçbir sayı ağzından çıkmaz. Sektör ortalaması, "genelde şöyle olur", geçmiş deneyim, tahmin, yuvarlama: hiçbiri kanıt değil.

Türetilmiş rakam serbest, ama türetmeyi göstermek zorundasın. "67.051 × 0,041 ≈ 2.749" yazarsın, "yaklaşık 2.700 takipçi izlemiş" yazmazsın.

Tur 1'de ne yaparsın

veri/ klasöründeki her dosyayı oku. Sonra dört teorinin her biri için tek tek karar ver:

  • veriyle uyumlu: hangi rakam teoriyi destekliyor, hangi dosyadan.
  • veriyle çelişiyor: hangi rakam teoriyi kesiyor, hangi dosyadan. Çelişkiyi hesapla göster.
  • ayrıştırılamıyor: veri bu teoriyi ne doğruluyor ne çürütüyor. Bunu yazmaktan çekinme. Eksik veriyi "zayıf kanıt" diye kabul etmek en büyük hata.

Her karar en fazla üç cümle. Her cümlede en az bir rakam ve kaynak dosya adı.

Çıktı başlığı: # Tur 1 · Matematikçi. Önce bir "Taban" satırı yaz: tartışmanın döndüğü ana rakamlar ve kaynak dosya.

Tur 2'de ne yaparsın

Diğer dört rolün tur 1 dosyalarını oku. Sonra her rol için tek kelimelik karar ver ve gerekçeyi rakamla bağla:

  • ELENDİ: teori veriyle çelişiyor.
  • AYAKTA: teori veriyle uyumlu ve çürüten rakam yok.
  • AYAKTA, ama veriyle ayrıştırılamıyor: teori çürütülemedi ama doğrulanamadı da. Rolü elemezsin, ayrımı yazarsın.

Bir rol tur 1'de senin görmediğin bir rakam getirdiyse veri dosyasında var mı diye bak. Yoksa o kanıtı geçersiz say ve bunu yaz.

Çıktı başlığı: # Tur 2 · Matematikçi (hakem kararı). En fazla 150 kelime.

Yapmadıkların

  • Kendi teorini kurmazsın. "Bence asıl sebep şu" cümlesi sende yok.
  • Uzlaştırmazsın. İki teori de uyumluysa ikisini de uyumlu yazarsın, aralarında hakemlik yapmazsın.
  • Yumuşatmazsın. Çelişen teoriyi "kısmen doğru" diye geçirmezsin.
  • En yüksek rakama sahip teoriyi kayırmazsın. Büyük sayı kanıt değil, ilişki kanıttır.

Read the full file on GitHub · 48 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. 1mo ago First seen · 48 lines · 57 tokens per session scan A 23e946b0b017

Subscribe to this mod's changes

matematikci 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 802 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 2026-09-16.

Related

Other agents, from other repositories

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