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.
git 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/commands/komunite/kalfa/unstick)<a href="https://agentmods.dev/commands/komunite/kalfa/unstick"><img src="https://agentmods.dev/badge/commands/komunite/kalfa/unstick.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00609 |
| Opus 5 | $0.00006 | $0.00304 |
| Sonnet 5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
unstick 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.
What it actually says
Bir engeli aş. Kök neden analizi ve yeni yaklaşımlar için Çözümleyici agent'ını kullanır.
Adımlar
Adım 1: Takılma durumunu yakala
Kullanıcı neye takıldığını anlattıysa onu kullan. Aksi halde şuralardan çıkar:
- Mevcut memory.md → Şimdi
- Son günlük not girdileri
- Bağlamdaki son birkaç araç çağrısı
Engeli bir cümlede ifade et: "[Y] nedeniyle [X]'de takıldım."
Adım 2: Engeli sınıflandır
| Tür | Sinyaller | Yaklaşım |
|---|---|---|
| Bilgi boşluğu | "Nasıl yapılacağını bilmiyorum..." | Belgeleri ara, kaynağı oku, Bilgi Tabanı'nı kontrol et |
| Karar felci | "Aralarında karar veremiyorum..." | Avantaj/dezavantajları listele, geri alınabilir seçeneği seç |
| Döngüsel debug | Aynı hata 3+ kez | Geri adım at, problemi yeniden ifade et, zıt yaklaşımı dene |
| Kapsam karmaşası | "Bu düşündüğümden büyük" | Kapsam Bekçisi kontrolü — doğru problemi mi çözüyorsun? |
| Çevresel | Build/deploy/config sorunları | Günlükleri kontrol et, ön koşulları doğrula, temiz durumu dene |
Adım 3: Çözümleyici'yi devreye sok
Çözümleyici agent'ını başlat:
Agent(unsticker): [problem]'de takıldım.
Denediklerim: [denemeleri listele]
Hata/belirti: [ne oluyor]
Beklenen: [ne olması gerekiyor]
Bunu parçala. Neyi kaçırıyorum?
Adım 4: Öneriyi uygula
Çözümleyici'nin en iyi önerisini al ve hemen dene. Kararsız kalma — harekete geç. Takılmaktan çıkmanın en hızlı yolu ilerlemektir.
Adım 5: Çözümü kaydet
Çözüldüyse, günlük nota ekle:
### Çözüm — SS:DD
- **Engel:** [ne takılmıştı]
- **Kök neden:** [neden]
- **Düzeltme:** [ne işe yaradı]
Düzeltme bir kalıp ortaya çıkarıyorsa, knowledge-nominations.md'ye aday göster.
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 · 65 lines · 12 tokens per session scan A a9b4da312d67
unstick is a command published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 609 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 2026-08-30.
Other commands, from other repositories
sniff-bloaters
Detect bloaters smells (Long Method, Large Class, Long Parameter List) using deterministic heuristics and append findings to .sniff/findings.jsonl.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.