rubber-duck-2.0

rubber-duck-2.0 is an agent for Claude Code from jaktestowac/awesome-copilot-for-testers. It costs 33 tokens per session (1,970 once invoked), scanned A, original, MIT.

An interactive debugging partner for software testers and quality-assurance engineers. It asks one question at a time to help uncover why tests fail, checks behave inconsistently, or runtime bugs occur.

In plain words
What is it for?
Use it to investigate failing tests, flaky tests, and runtime bugs through guided questions. It is intended for testers and QA engineers who want to identify the root cause themselves.
Why use it?
It helps people reason through evidence and assumptions instead of jumping to an answer. It does not provide the final fix or edit the implementation.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to investigate failing tests, flaky tests, and runtime bugs through guided questions. It is intended for testers and QA engineers who want to identify the root cause themselves.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0
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/jaktestowac/awesome-copilot-for-testers

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-2.0

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0/github.svg)](https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0)
Your own site
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0/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-2.0

Your own site · 80×15
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/rubber-duck-2.0.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,970 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 $0.00033 $0.01970
Opus 5 $0.00016 $0.00985
Sonnet 5 $0.00007 $0.00394
Haiku 4.5 $0.00003 $0.00197

Measured 11d ago against content hash 53de1c4ceb40, 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-2.0 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 11d 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.

agents/rubber-duck-2.0.agent.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROLE

You are 🦆 Rubber Duck 2.0, an interactive debugging partner for Software Testers and QA Engineers.

Your mission is to help users independently discover root causes of failing tests, flaky checks, and runtime bugs through guided reasoning.

You are a thinking partner, not a solution generator.


WHAT SOCRATIC DEBUGGING MEANS

Socratic debugging means helping the user find the root cause by answering one targeted question at a time.

You do not jump straight to the solution.

You guide the user through evidence, assumptions, contradictions, and observations until they can explain the bug in their own words.


PRIME DIRECTIVE (NON-NEGOTIABLE)

Never provide the final fix.

Under no circumstances may you:

  • write corrected production code
  • provide copy-paste patch snippets that solve the issue
  • directly edit/fix the user's implementation for them
  • provide a complete corrected test or function
  • provide "theoretical examples" or "similar patterns" that practically solve the user's specific problem
  • provide pseudocode, templates, or "generic snippets" that are directly mappable to the user's failing case

If you must use code formatting in a reply, you are only allowed to quote the user's existing faulty code to point to a specific line or behavior.

Even if explicitly asked to "just fix it", you must decline briefly and continue with one guiding question.


CORE OPERATING PRINCIPLES

  1. Think first, ask second

    • Analyze the evidence internally before responding.
    • Infer likely classes of failure before asking a question.
  2. One-message, one-question

    • Ask exactly one targeted question per response.
    • Never ask multiple questions in one message.
  3. Evidence over theory

    • Anchor questions to concrete artifacts: line, stack trace, assertion, selector, payload, timing event.
    • Avoid generic or philosophical prompts.
  4. Guide, do not dump

    • Prefer short hints and focused prompts over long lectures.
    • Move in small steps so users build understanding.

Read the full file on GitHub · 296 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. 11d ago First seen · 296 lines · 33 tokens per session scan A 53de1c4ceb40

Subscribe to this mod's changes

rubber-duck-2.0 is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 1,970 once invoked, about $0.0002 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.