retro

retro is a command for Claude Code from komunite/kalfa. It costs 25 tokens per session (769 once invoked), scanned A, original, MIT.

Sprint retrospective command that reviews a period of software work to identify what went well, what went wrong, and what should change. A sprint retrospective is a team review held after a work period to improve the process.

In plain words
What is it for?
Use it to review recent work, find repeated failures and bottlenecks, assess task completion and session quality, and propose process or tooling improvements.
Why use it?
It turns scattered work notes, incidents, failures, and completion data into recurring patterns instead of relying on memory or isolated opinions.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/komunite/kalfa/retro
Clone the repo
git clone --depth 1 https://github.com/komunite/kalfa

Made for: Claude Code.

Wrote 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.

agentmods badge for retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/komunite/kalfa/retro.svg)](https://agentmods.dev/commands/komunite/kalfa/retro)
Your own site
<a href="https://agentmods.dev/commands/komunite/kalfa/retro"><img src="https://agentmods.dev/badge/commands/komunite/kalfa/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00769
Opus 5 $0.00013 $0.00385
Sonnet 5 $0.00005 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 4d ago against content hash 76c31d4c5a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retro 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 4d 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.

.claude/commands/retro.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospektif analiz. Bir zaman dilimini incele, kalıpları çıkar, sistemi iyileştir.

Adımlar

Adım 1: Kapsamı belirle

Kullanıcı bir zaman dilimi belirttiyse onu kullan. Aksi halde varsayılan "bu hafta."

Adım 2: Verileri topla (paralel okumalar)

Eşzamanlı oku:

  • Son günlük notlar (son 5-7 gün)
  • .claude/logs/verdicts.jsonl (oturum kalite trendleri)
  • .claude/logs/incident-log.md (sorunlar ve engeller)
  • .claude/logs/failure-log.md (araç başarısızlıkları)
  • .claude/knowledge-nominations.md (bekleyen öğrenimler)
  • .claude/workspace/TaskBoard.md (tamamlanma oranı)

Adım 3: Kalıpları analiz et

Ne iyi gitti?

  • Zamanında tamamlanan görevler
  • Sorunsuz iş akışları (engel yok)
  • Başarıyla yakalanan öğrenimler
  • Pozitif yönde seyreden kalite değerlendirmeleri

Ne iyi gitmedi?

  • Tekrarlayan başarısızlıklar (aynı hata türü)
  • İzin verilmesi gereken engellenen komutlar
  • Beklenenden çok daha uzun süren görevler
  • Sık ihtiyaç duyulan bağlam temizleme (/clear)
  • Kalite değerlendirme engelleri

Ne değişmeli?

  • Süreç darboğazları var mı?
  • Hook'lar çok mu sıkı yoksa çok mu gevşek?
  • Agent'larda eksik yetenekler var mı?
  • Eksik veya az kullanılan komutlar var mı?

Adım 4: İyileştirmeleri çıkar

Belirlenen her iyileştirme için:

  1. Bilgi Tabanı kuralı mı? → Doğrudan terfi ettir
  2. Süreç değişikliği mi? → Kullanıcı incelemesi için Not Defteri'ne ekle
  3. Araç/config değişikliği mi? → Görev Panosu'nda görev oluştur
  4. İzlenecek kalıp mı? → Bilgi Adaylıkları'na aday göster

Adım 5: Retrospektif raporunu yaz

Günlük nota ekle:

## Retrospektif — [dönem]

### İyi Giden
- [maddeler]

### İyi Gitmeyen
- [maddeler]

### Eylem Kalemleri
- [ ] [sorumlusuyla belirli iyileştirme]

### Metrikler
- Tamamlanan görevler: [X]
- Kalite değerlendirme geçiş oranı: [X]%
- Olaylar: [X] (CRITICAL: [X], HIGH: [X])
- Bağlam temizlemeleri: [X]

Adım 6: Eylem kalemlerini oluştur

Eyleme dönüştürülebilir iyileştirmeleri .claude/workspace/TaskBoard.md → Bu Hafta'ya ekle.

Read the full file on GitHub · 86 lines

Changes

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.

  1. 4d ago First seen · 86 lines · 25 tokens per session scan A 76c31d4c5a3b

Subscribe to this mod's changes

retro is a command published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 769 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.