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 fthsrbst/mnema --skill architectgit clone --depth 1 https://github.com/fthsrbst/mnemaWrote 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/fthsrbst/mnema/architect)<a href="https://agentmods.dev/skills/fthsrbst/mnema/architect"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/architect/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/fthsrbst/mnema/architect"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/architect.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 | $0.00057 | $0.00602 |
| Opus 5.5 | $0.00023 | $0.00241 |
| Sonnet 5.5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
architect 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.
What it actually says
Architect — Önce Tasarım, Sonra Kod
Orta+ büyüklükte her iş için: koda atlamadan önce bu akışı çalıştır.
Akış
- Geçmişi tara:
memory_search(type=decision)+project_get— benzer karar daha önce verilmiş mi? Fatih'in stack tercihleri neler? Çelişen karar üretme; değiştireceksen gerekçesiyle değiştir. - Gereksinimleri sıkıştır: İşlevsel (ne yapacak) + işlevsel olmayan (ölçek, gecikme, maliyet, offline?) — bilinmeyenleri kullanıcıya TEK turda sor, sorularla süründürme.
- Veri modelinden başla: Varlıklar, ilişkiler, yaşam döngüsü. Veri modeli doğruysa kodun yarısı bitmiştir; API ve UI ondan türer.
- Sınırları çiz: Modül/servis sınırları, kim kiminle konuşur, hangi katman neyi bilmez. Tek cümleyle söylenemeyen sorumluluk = yanlış sınır.
- En basit mimariyi seç, ölçek yolunu not et: "Şimdilik SQLite; 1M kayıtta Postgres'e geçiş şurası değişir" tarzı. Bugünün problemi için kur, yarının problemi için kapı bırak (soyutlama katmanı değil — sadece temiz arayüz).
- Kararları yaz: Her önemli seçim için
memory_save(type=decision)+project_add_decision: seçenek, seçilen, gerekçe, ret nedenleri. Format: "YYYY-MM: X seçildi — gerekçe; Y reddedildi çünkü ...". - Doğrulama planı: Mimarinin en riskli varsayımı ne? Onu ilk sprint'te ucuz bir spike ile test et.
Refleksler
- İki benzer teknoloji arasında kararsızsan: ekosistem olgunluğu + Fatih'in mevcut bilgisi > yenilik parlaklığı.
- Soyutlamayı ikinci tekrarda ekle, ilk yazımda değil ([[code-conventions]]).
- Dış servis/API entegrasyonunda: timeout, retry, degrade davranışı tasarımın parçası — sonradan eklenti değil.
- Mimari dokümanı kısa tut: 1 diyagram + karar listesi + veri modeli. Uzun doküman okunmaz, güncellenmez.
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.
- 1mo ago First seen · 24 lines · 57 tokens per session scan A c03258e98a44
architect is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 602 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 2026-08-31.
Other skills, from other repositories
zootopia-ppt
A presentation-making workflow that turns a speech or slide content into images showing an animated world of human-like animals. It first plans each slide and then generates the slide images.
kanban-tasks
A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.
ocr
OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize characters in an image file (.jpg, .jpeg, .png, .gif, .webp). Requires QWENAPIKEY and…
daily-digest
Build a daily digest from curated sources. Follow the output contract strictly.
duckdb-analyst
Use for any analytical question over ./data/.parquet. Prefer DuckDB, always show the SQL.
onboard
Link this project to a Pad workspace and set it up.