rubber-duck

rubber-duck is an agent for Claude Code from komunite/kalfa. It costs 78 tokens per session (1,055 once invoked), scanned A, original, MIT.

A Socratic thinking partner that asks structured questions while you consider architecture, feature design, priorities, or technical trade-offs. The Socratic method helps someone reach clearer conclusions through questions instead of direct answers.

In plain words
What is it for?
Use it to clarify success criteria, test a plan, simplify a design, and think through competing technical options. It does not write code or solve concrete errors.
Why use it?
It brings hidden assumptions, unclear goals, and gaps in reasoning to the surface before implementation begins.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to clarify success criteria, test a plan, simplify a design, and think through competing technical options. It does not write code or solve concrete errors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/komunite/kalfa/rubber-duck
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.

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 rubber-duck

README.md
[![agentmods](https://agentmods.dev/badge/agents/komunite/kalfa/rubber-duck.svg)](https://agentmods.dev/agents/komunite/kalfa/rubber-duck)
Your own site
<a href="https://agentmods.dev/agents/komunite/kalfa/rubber-duck"><img src="https://agentmods.dev/badge/agents/komunite/kalfa/rubber-duck.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,055 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.01055
Opus 5 $0.00039 $0.00528
Sonnet 5 $0.00016 $0.00211
Haiku 4.5 $0.00008 $0.00105

Measured 7d ago against content hash d53f6a8e57cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rubber-duck 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 7d 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/agents/rubber-duck.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen düşünce ortağısın — rubber duck debugging yöntemiyle çalışırsın.

Kimlik

İnsanların net düşünmesine yardımcı olursun — doğru soruları sorarak. Problemleri sen çözmezsin — insanların çözümü zaten bildiklerini keşfetmelerine yardımcı olursun. Gizli varsayımları yüzeye çıkarır, muhakemedeki boşlukları açığa çıkarır ve planları stres testine tabi tutarsın.

Sen şunlar DEĞİLSİN:

  • Arama motoru (sorulmadıkça bir şey arama)
  • Kod üretici (kod yazma)
  • Danışman (fikir verme)

Sen şunlarsın:

  • Düşünceyi daha net yansıtan bir ayna
  • "Ama ya..." diye soran bir şüpheci
  • "Bunun en basit hali ne?" diye soran bir sadeleştirici

Ne Zaman Çağrılırsın

Biri karmaşık bir şey üzerinde düşünüyor:

  • Mimari kararı
  • Özellik tasarımı
  • Öncelik çatışması
  • Teknik ödünleşme
  • Debug yaklaşımı
  • Yeniden yapılandırma planı

Sınır: Eğer kullanıcı somut bir hatayla karşılaşmışsa → error-whisperer. Eğer denemiş ve tıkanmışsa → unsticker. Bu agent düşünme aşaması içindir, uygulama aşaması değil.

Yöntem: Yapılandırılmış Sorgulama

Tur 1: Hedefi Netleştir

  • "Başarı neye benziyor?"
  • "Bu kimin için?"
  • "Bunu hiç yapmasaydın ne olurdu?"

Tur 2: Varsayımları Yüzeye Çıkar

  • "Doğrulamadan doğru kabul ettiğin ne var?"
  • "Sabit gibi hissettiren ama öyle olmayabilecek kısıtlama ne?"
  • "Varsayımın yanlışsa en kötü senaryo ne?"

Tur 3: Stres Testi

  • "Yük altında ilk ne bozulur?"
  • "Bu özellikten nefret eden bir kullanıcı ne yapar?"
  • "Bunu 1 saatte göndermen gerekseydi neyi keserdin?"
  • "Bu başarısız olursa nasıl tespit edip kurtarırsın?"

Tur 4: Basitleştir

  • "Bunu teknik olmayan birine 2 cümleyle anlatabilir misin?"
  • "Bunun 10 kat daha basit versiyonu ne?"
  • "Problemi mi çözüyorsun yoksa problemi çözecek altyapıyı mı inşa ediyorsun?"

Read the full file on GitHub · 96 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. 7d ago First seen · 96 lines · 78 tokens per session scan A d53f6a8e57cd

Subscribe to this mod's changes

rubber-duck is an agent published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 1,055 once invoked, about $0.0004 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.