rubber-duck

rubber-duck is a skill for Claude Code from Osipchuk/agent-skills. It costs 145 tokens per session (464 once invoked), scanned A, original, MIT.

A guided conversation that helps you work out your own answer by explaining the problem aloud. It listens first, asks focused questions, and becomes more direct only when you are stuck or ask for an answer.

In plain words
What is it for?
Thinking through bugs, designs, decisions, and confusing problems; explaining what happened; checking assumptions; and finding the gap that is blocking progress.
Why use it?
It helps reveal hidden assumptions and missing facts without immediately taking over the reasoning. This can make debugging and design thinking clearer while keeping the decision with you.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills plugin — 8 skills shipped together

Good fit Thinking through bugs, designs, decisions, and confusing problems; explaining what happened; checking assumptions; and finding the gap that is blocking progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/osipchuk/agent-skills/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.

Any agent
npx skills add Osipchuk/agent-skills --skill rubber-duck
Clone the repo
git clone --depth 1 https://github.com/Osipchuk/agent-skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 8 skills.

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/skills/osipchuk/agent-skills/rubber-duck/github.svg)](https://agentmods.dev/skills/osipchuk/agent-skills/rubber-duck)
Your own site
<a href="https://agentmods.dev/skills/osipchuk/agent-skills/rubber-duck"><img src="https://agentmods.dev/badge/skills/osipchuk/agent-skills/rubber-duck/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.

agentmods 80×15 button for rubber-duck

Your own site · 80×15
<a href="https://agentmods.dev/skills/osipchuk/agent-skills/rubber-duck"><img src="https://agentmods.dev/badge/skills/osipchuk/agent-skills/rubber-duck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 464 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 $0.00145 $0.00464
Opus 5 $0.00072 $0.00232
Sonnet 5 $0.00029 $0.00093
Haiku 4.5 $0.00015 $0.00046

Measured 10d ago against content hash abeacf1cd7b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

skills/rubber-duck/SKILL.md · 39 lines

What it actually says

rubber-duck

Help the person solve it themselves. The act of articulating a problem to something that won't just answer is what surfaces the solution. Start as a silent-ish duck; grow teeth only when they're spinning.

The escalation ladder

Gear 0 — Listen. Invite them to explain the problem as if to someone who knows nothing about it. Reflect back the key facts and the implicit assumptions you heard them make. Very often the answer surfaces right here — let it; don't rush to question.

Gear 1 — Clarify. Ask narrow, factual questions about what they've actually observed or already tried — not "what do you think it is?". One question per turn. Let them do the reasoning between your questions.

Gear 2 — Teeth. Only when they're repeating themselves, clearly stuck, or pushing for the answer: ask the one pointed question that exposes the gap in their reasoning. Still do not supply the fix.

The escape hatch

If they explicitly ask you to stop and just answer (roughly twice), or it's plainly an emergency, drop the method and answer directly. Insisting on the method past its usefulness is the failure mode, not a virtue.

Never

  • Dump the solution in Gear 0 or 1.
  • Ask more than one question per turn.
  • Withhold to seem clever. The goal is their insight, not your cleverness.
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. 10d ago First seen · 39 lines · 145 tokens per session scan A abeacf1cd7b1

Subscribe to this mod's changes

rubber-duck is a skill published in the GitHub repository Osipchuk/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 464 once invoked, about $0.0007 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 2026-08-31.