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 komunite/kalfa --skill gmail-takip-sistemigit clone --depth 1 https://github.com/komunite/kalfaWrote 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/komunite/kalfa/gmail-takip-sistemi)<a href="https://agentmods.dev/skills/komunite/kalfa/gmail-takip-sistemi"><img src="https://agentmods.dev/badge/skills/komunite/kalfa/gmail-takip-sistemi/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/komunite/kalfa/gmail-takip-sistemi"><img src="https://agentmods.dev/badge/skills/komunite/kalfa/gmail-takip-sistemi.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 | $0.00023 | $0.00992 |
| Opus 5 | $0.00012 | $0.00496 |
| Sonnet 5 | $0.00005 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
gmail-takip-sistemi 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Takip Sistemi
Amaç
Gmail'deki gönderilmiş e-postaları tarayıp henüz cevap gelmemiş olanları tespit eder. Her birine uygun takip e-postası taslağı hazırlar. Solopreneur'ların en büyük gelir kaçağı olan "cevap gelmedi, unuttum" sorununu çözer.
Kategori: Yapay Zeka ve Otomasyon MCP Gereksinimi: Gmail MCP bağlı olmalı
Süreç
Adım 1: Takip bekleyen e-postaları bul
Gmail MCP gmail_search_messages ile şu aramaları yap:
in:sent after:7d— son 7 günde gönderilenin:sent -in:inbox— cevap gelmemiş olanlar (yanıt geldiyse inbox'ta thread görünür)
Veya daha spesifik:
in:sent subject:(teklif OR proposal OR fiyat OR görüşme) after:3d— iş e-postaları
Adım 2: Önceliğe göre sınıflandır
Her cevapsız e-postayı şu kategorilere ayır:
| Öncelik | Kural | Eylem |
|---|---|---|
| ACİL | Teklif/proposal gönderilmiş, 48+ saat cevap yok | Bugün takip et |
| YÜKSEK | Müşteri/lead ile görüşme, 3+ gün cevap yok | Bu hafta takip et |
| NORMAL | Genel iletişim, 5+ gün cevap yok | Hafta sonu takip et |
| BIRAK | Soğuk outreach, 7+ gün cevap yok | Artık takip etme |
Adım 3: Takip e-postası taslakları oluştur
Her ACİL ve YÜKSEK e-posta için takip taslağı hazırla:
Takip #1 (48 saat sonra):
Konu: Re: [orijinal konu]
Merhaba [isim],
Geçen gönderdiğim [konu] hakkında bir güncelleme var mı diye merak ettim.
Sorularınız varsa memnuniyetle cevaplayabilirim.
[imza]
Takip #2 (5 gün sonra):
Konu: Re: [orijinal konu]
Merhaba [isim],
[Konu] hakkındaki e-postamı görme şansınız oldu mu?
Eğer zamanlaması uygun değilse anlayışla karşılarım — ileride tekrar konuşmak isterseniz haber vermeniz yeterli.
[imza]
Takip #3 (10 gün sonra — son):
Konu: Re: [orijinal konu]
Merhaba [isim],
Bu konuda son bir kez ulaşmak istedim. Eğer şu an öncelikleriniz arasında değilse sorun değil.
İleride ihtiyacınız olursa buradayım.
[imza]
Adım 4: Taslakları kaydet
Kullanıcı onayıyla Gmail MCP gmail_create_draft ile taslakları oluştur. Her taslak orijinal thread'e yanıt olarak ayarlansın.
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.
- 8d ago First seen · 116 lines · 23 tokens per session scan A 902f877c3443
gmail-takip-sistemi is a skill published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 992 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other skills, from other repositories
agent-estate
Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
angle-generator
Turn a company update into 3-7 structurally distinct, journalist-shaped story angles. Runs the fact through proven newsroom lenses (perspective, abstraction, news values, data, contrarian, news peg) and refuses rephrasings, invented facts, named-journalist guesses, and AI-marketing slop.
journalist-fit-check
Gate a pitch against one journalist at a time. Runs the pair through proven media-relations checks (last-10-bylines audit, 90-day topic sweep, beat-vs-angle-vs-one-off, the 5 forms of journalism, source-mirror, stated-preferences, database triangulation) and returns fit, soft-fit, no-fit, or unknown with a real recent…
macos-storage-management
Safely reclaim local Mac storage without mistaking cloud placeholders for resident data, losing File Provider content, or flattening metadata onto an incompatible external filesystem.
token-saver
Skill to implement token saving scheme, concise, and focused on essential changes / Skill untuk menerapkan skema penghematan token, ringkas, dan fokus pada perubahan esensial tanpa basa-basi.
project-context-mapper
Gives the agent a photographic memory of massive repositories. Forces the creation and maintenance of a highly compressed CONTEXTMAP.md to prevent context exhaustion and hallucination.