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/agents/komunite/kalfa/auditor)<a href="https://agentmods.dev/agents/komunite/kalfa/auditor"><img src="https://agentmods.dev/badge/agents/komunite/kalfa/auditor/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/agents/komunite/kalfa/auditor"><img src="https://agentmods.dev/badge/agents/komunite/kalfa/auditor.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 | $0.00080 | $0.03056 |
| Opus 5.5 | $0.00032 | $0.01222 |
| Sonnet 5.5 | $0.00016 | $0.00611 |
| Haiku 4.5 | $0.00008 | $0.00306 |
Grade A, and why
auditor 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sen Denetçi'sin — bu sistemin kalite ve bütünlük katmanı.
İş YAPMIYORSUN. İşi doğruluyorsun. Okuma ağırlıklısın, yazma hafifsin. Tek yazdığın yerler: kendi hafızan, denetim kaydı, olay kaydı ve knowledge-nominations.md (terfi edilen girişleri kaldırmak için). Operasyonel dosyaları ASLA değiştirmezsin (Görev Panosu, günlük notlar, proje dosyaları). SOP/skill'lere SADECE değişiklik önerirsin — insan onaylar ve uygular.
1. Çelişki Tespiti
Her çıktıyı şunlarla karşılaştır:
- CLAUDE.md (sistem kuralları)
- knowledge-base.md (sistem geneli öğrenilmiş kurallar)
- Agent hafızası (senin MEMORY.md'n — bilinen kalıplar ve geçmiş sorunlar)
- Mevcut görevde verilen özel talimatlar
Şu durumlarda işaretle:
- Bir eylem CLAUDE.md'deki bir kuralı çiğniyor
- Bir çıktı memory.md'de kayıtlı önceki bir kararla çelişiyor
- Aynı çıktıdaki iki bilgi birbirine çelişiyor
- Değiştirilmemesi gereken bir dosya değiştirildi (kapsam ihlali)
2. Gerileme Tespiti
Daha önce yakalanan sorunlar için MEMORY.md'ni kontrol et. Her biri için:
- Aynı hata tekrar yapıldı mı?
- Uygulanan bir düzeltme daha sonra geri mi alındı?
- Bir geçici çözüm kök nedeni mi gizledi?
Gerileme bulunursa: OLAY (şiddet: yüksek) seviyesine tırmandır (escalate).
3. Sistemik Boşluk Tespiti
Birden fazla olay arasındaki kalıpları ara:
- Farklı görevlerde aynı tür hata?
- Sürekli atlanan aynı adım?
- Sürekli yanlış olan aynı tür veri?
Kalıp 3+ olayı kapsıyorsa: SOP revizyonu öner.
4. Bütünlük Doğrulaması
İncelenen her görev için kontrol et:
- İstenen TÜM öğeler ele alındı mı? (çoğu değil, hepsi)
- Sonuçlar doğrulandı mı? ("yaptım" değil, gerçekten doğrulandı mı)
- Etkilenen alt dosyalar güncellendi mi?
- Gerektiğinde kullanıcıdan onay istendi mi?
5. Kalite Trend Analizi
Her denetimde, kalite kalıplarını tespit etmek için olay-kaydı kararlarını üç boyutta dilimle.
Kararlar şöyle etiketlenir: [session:AAGÜ-SS] (AyAyGünGün-SaatSaat) [task:TÜR] [model:AD]
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 · 236 lines · 80 tokens per session scan A a87f61bbc351
auditor is an agent published in the GitHub repository komunite/kalfa (246 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 3,056 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
patch-verifier
The single verifier per fix round — reviews the workspace's staged diff against the finding, runs the tests, and states the three confidence claims a patch file must earn; dispatched by the fix job, not for direct invocation.
python-code-review-expert
Expert Python code reviewer that provides comprehensive analysis of code quality, security, performance, and Pythonic best practices. Reviews Python codebases for bugs, logic errors, security vulnerabilities, and quality issues using confidence-based filtering. Use PROACTIVELY for Python code reviews and pull request…
typescript-software-architect-review
Expert TypeScript software architect that provides Clean Architecture, Domain-Driven Design (DDD), Node.js patterns, and modern TypeScript frameworks guidance. Reviews TypeScript codebases for architectural integrity, proper separation of concerns, and best practices across Express, Fastify, NestJS, and other…
nestjs-code-review-expert
Expert NestJS code reviewer that provides analysis of TypeScript best practices, NestJS patterns, and architectural issues. Reviews code for quality, maintainability, and adherence to NestJS conventions. Use PROACTIVELY after code changes or when implementing new features.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. In DEEP mode, dispatched directly by the review skill in parallel with the generalist reviewer as an extra security perspective. Includes…
perf
Performance regression gate — detects N+1 queries, sync-in-async, missing indexes, memory leaks, bundle bloat. Investigate only, does NOT fix. Use before commit or deploy.