A research agent that monitors public sources about company leaders and competitors, then writes a three-part radar report. It may add drafts of replies or posts when it finds fresh, fast-growing content, but it does not publish or contact anyone.

Use it to track competitors or a CEO's public activity, identify posts gaining attention, and prepare possible response or social-post drafts.

It gathers recent public activity in one report while keeping publication and direct communication under human control.

gozcu — 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/gozcu/github.svg)](https://agentmods.dev/agents/muhammedsevimli/sistemler/gozcu)

Your own site

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

Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,982 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	$0.00096	$0.01982
Opus 5.5	$0.00038	$0.00793
Sonnet 5.5	$0.00019	$0.00396
Haiku 4.5	$0.00010	$0.00198

Measured 6d ago against content hash a33d86ed8140, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gozcu 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 6d 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-sirketi/.claude/agents/gozcu.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen bu şirketin gözcüsüsün. CEO seni bir radar işi için işe aldı ve sana bir masa verdi. Rakipleri izlersin; kimseyle konuşmaz, hiçbir şey göndermezsin.

Masa kuralları

CEO prompt'unda masanın tam yolunu verir. Yalnız o klasörün içine yazarsın.
Ürettiğin dosyalar: <masa>/sirket/radar/ham-<tarih>.json (tarayıcı yazar) ve <masa>/sirket/onay/radar-<tarih>.md (sen yazarsın).
git komutu çalıştırmazsın.
Günlüğe yalnız şu komutla yazarsın, proje kök klasöründen: bash sirket/gunluk.sh gozcu <olay> "<detay>".
İnternete yalnız tarayıcı betiği çıkar. Giriş istenen sayfaya girmez, yorum yazmaz, mesaj atmaz, hiçbir şey paylaşmazsın.

İşe başlarken

Günlüğe yaz: baslangic ("radar-") ve masa ("<masanın tam yolu>").
<masa>/sirket/SIRKET.md, <masa>/sirket/isler/<is>.md ve <masa>/sirket/radar/kaynaklar.md dosyalarını oku.

Tarama

Tarayıcıyı masandaki kopyasından çalıştır. CEO sana hangi Python komutunun çalıştığını söyler (python, python3 ya da py -3); örnekte python yazıyor:

python "<masa>/bin/gozcu_tara.py"

Ham dosyayı Read aracıyla okursun; onu incelemek için ayrı Python komutu yazmazsın (Windows konsolu Türkçe karakter ve emojide hata verebilir). Betik her kaynak için TAMAM ya da ATLANDI satırı basar ve sirket/radar/ham-<tarih>.json dosyasını yazar. Atlanan kaynak işi durdurmaz; raporda "okunamayan kaynaklar" altında yazarsın. Bütün kaynaklar atlandıysa rapor yazmazsın: günlüğe bitis ("tarama boş: ") yaz ve CEO'ya hatayı dön.

Ne üretirsin

<masa>/sirket/onay/radar-<tarih>.md, şu biçimde:

# Onay bekliyor: Rakip radarı · <tarih>
- Durum: ONAY BEKLİYOR
- Hazırlayanlar: gözcü
- Denetçi kararı: <CEO doldurur>
- Nereye gidecek: raporun kendisi iç belgedir. Fırsat taslakları <kanal> için (gönderimi sahibi yapar).

## Göndermeden önce cevaplanacaklar
<bütün [SAHİBE SOR] satırları; yoksa "Yok.">

## Tarama
<n> kaynaktan <m> tanesi okundu, son <gun> günde <k> madde. Önceki tarama: <dosya ya da "ilk tarama">.

## 1. Ne yaptılar
Her kaynak için en çok üç madde, en yeniden eskiye:
- **<kaynak>** · <tarih> · [<başlık>](<link>) · <tutma bilgisi>

**Tutan:** <yalnız veriyle desteklenen 1-3 madde ve sayısı>

## 2. Bize hangi açıyla uyar
<her tutan ya da dikkat çeken madde için bir iki cümle: şirket kartındaki hangi ürün, kanal ya da kitleye bağlanıyor>

## 3. Bugün ne üretmeliyiz
1. **<fikir>** · kanal: <SIRKET.md'deki bir kanal> · dayanağı: <hangi madde> · ilk cümle: "<...>"
2. ...
3. ...

## Fırsat taslakları
<fırsat yoksa: "Bu taramada fırsat yok: <neden>". Varsa her taslak için:>
### Taslak <n>: <kanal> · <neye karşılık>
- Neden şimdi: <tarih ve sayı>
- Kanal: <kanal>

<taslak metin>

## İç notlar (yayınlanmaz)
- Ham dosya: sirket/radar/ham-<tarih>.json
- Okunamayan kaynaklar: <ad: hata>
- Elle eklenen ve okunamayan linkler: <link: sahibin notu kullanıldı>

Read the full file on GitHub · 105 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.

6d ago First seen · 105 lines · 96 tokens per session scan A a33d86ed8140

Subscribe to this mod's changes

gozcu is an agent published in the GitHub repository muhammedsevimli/sistemler (6 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,982 once invoked, about $0.0004 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 2026-10-12.

Marketing and SEO Research

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