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.
npx skills add yildirimozal/ajanox --skill delete-old-logsgit clone --depth 1 https://github.com/yildirimozal/ajanoxWrote 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.
[](https://agentmods.dev/skills/yildirimozal/ajanox/delete-old-logs)<a href="https://agentmods.dev/skills/yildirimozal/ajanox/delete-old-logs"><img src="https://agentmods.dev/badge/skills/yildirimozal/ajanox/delete-old-logs/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.
<a href="https://agentmods.dev/skills/yildirimozal/ajanox/delete-old-logs"><img src="https://agentmods.dev/badge/skills/yildirimozal/ajanox/delete-old-logs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00030 | $0.00836 |
| Opus 5 | $0.00015 | $0.00418 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade B, and why
delete-old-logs scanned grade B with 1 finding 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Permission denied (sistem koruması): "İzin hatası: <detay>" — sudo isteme What it actually says
Delete Old Logs Skill
Belirli bir klasörde N günden eski log dosyalarını bulup siler. Bu, klasik "30 günden eski log dosyalarını sil" senaryosunun referans implementasyonudur.
Parametreler
klasor(zorunlu): aranacak yol. Türkçe ifadeleri İngilizce'ye çevir:- "log klasörü" →
/var/log(Linux) veya~/Library/Logs(macOS) - "indirilenler" →
~/Downloads
- "log klasörü" →
gun(opsiyonel, default: 30): kaç günden eski
Çalıştırılacak komutlar (SIRAYLA, AYNI TURDA, DURMA)
Adım 1: Listele
find <klasor> -type f -name "*.log" -mtime +<gun>
Bu komut shell_safe — sessizce çalışır.
Adım 2: Hemen Sil (komut çıktısı boş değilse)
Kullanıcıya hiçbir şey sormadan, doğrudan rm çağır:
rm -f <dosya1> <dosya2> ...
<dosya1> <dosya2> yerine Adım 1'in çıktısındaki dosya yollarını koy.
KRİTİK: "Silmek istiyor musunuz?" diye SORMA. Doğrudan rm bash çağrısını yap. Çünkü:
rmshell_unsafe kategorisindedir- Ajanox güvenlik katmanı zaten runtime'da kullanıcıya görünür onay sorusu çıkaracak ([E]vet/[H]ayır/[T]ümü)
- Skill'in görevi komutu hazırlamak; kullanıcıyı onaylatmak ASLA SKILL'İN İŞİ DEĞİL — runtime'ın işi
- Eğer sorarsan: kullanıcı iki kere onay vermek zorunda kalır → kötü UX
Sonuç işleme
- rm başarılı (exit 0): "X dosya silindi" rapor et
- rm reddedildi (Ajanox güvenlik onay vermedi): "İşlem iptal edildi, dosyalar duruyor"
- Liste boştu: " günden eski log dosyası yok, silinecek bir şey yok"
Hata durumları
- Klasör yoksa: "Klasör bulunamadı: "
- Permission denied (sistem koruması): "İzin hatası: " — sudo isteme
- macOS
/var/logSIP korumalı;~/Library/Logsyazılabilir
Güvenlik notu
shell_unsafe ve file_write permission'larını gerektirir. Critical path
(~/.ssh, /etc, ...) altında bir log dosyasına dokunulursa Ajanox
ekstra onay katmanı devreye girer ve "T (Tümünü onayla)" opsiyonu KAPALI olur.
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.
- 12d ago First seen · 79 lines · 30 tokens per session scan B 7729b9b9451f
delete-old-logs is a skill published in the GitHub repository yildirimozal/ajanox (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 836 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
speicherbereinigung
Evidenzbasierte Windows-Speicherbereinigung mit kontrolliertem Notfallmodus, physischer Belegungsmessung, Prozess- und Entstehungsforensik sowie reversiblen Maßnahmen gegen wiederkehrende Speicherfüller.
folder-flattening
Verschachtelte Ordnerhierarchien in flache, maschinenlesbare Strukturen umbauen. Bash-basiert mit intelligenter Merge-Logik.
batch-file-ops
Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.
nulcleaner
Findet und löscht Windows-reservierte NUL-Dateien, die durch die Nutzung von /dev/null in Git Bash entstehen. Headless oder mit GUI.
folder-organization
Ordner und Dateiablagen semantisch aufräumen: lokale Regeln und vorhandene Taxonomie erkennen, Dateien inhaltlich zuordnen, zusammengehörige Sets erhalten, klare Vorgänger-/Nachfolgerreihen und Logs archivieren, gemischte gültige und überholte Inhalte per Cut-and-Clue trennen und Löschkandidaten reversibel in einen…
integration-test
Run a live-instance verification of traceway-cli that goes beyond the Go smoke suite — exercises real-data detail endpoints, TTY-default rendering, adaptive metric-name discovery, and emits a human-readable coverage report. Invoke ONLY when the user explicitly asks (e.g. "run integration tests", "verify the CLI…