rubber-ducky

rubber-ducky is a skill for Claude Code from harnessprotocol/harness-kit. It costs 186 tokens per session (2,069 once invoked), scanned A, original, Apache-2.0.

A built-in critic that reviews a planned or completed coding change, tests, or repeated debugging failures. It uses independent read-only reviewers to look for gaps and concrete problems.

In plain words
What is it for?
Use it to sanity-check a non-trivial plan, review a multi-file change, inspect newly written tests, or investigate failures that keep recurring.
Why use it?
It helps catch design flaws before implementation and find issues that may be missed by the agent that created the work. The feedback is organized so it can guide revisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the rubber-ducky plugin — 1 skill shipped together

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 skills/harnessprotocol/harness-kit/rubber-ducky
Any agent
npx skills add harnessprotocol/harness-kit --skill rubber-ducky
Clone the repo
git clone --depth 1 https://github.com/harnessprotocol/harness-kit

Made for: Claude Code.

Or install rubber-ducky, the plugin that ships this one along with the rest of its 1 skill.

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-ducky

README.md
[![agentmods](https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/rubber-ducky.svg)](https://agentmods.dev/skills/harnessprotocol/harness-kit/rubber-ducky)
Your own site
<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/rubber-ducky"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/rubber-ducky.svg" alt="Measured on agentmods" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,069 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 5.1 $0.00186 $0.02069
Opus 5 $0.00093 $0.01035
Sonnet 5 $0.00037 $0.00414
Haiku 4.5 $0.00019 $0.00207

Measured 6d ago against content hash d702a89035bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

rubber-ducky 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 6d 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.

plugins/rubber-ducky/skills/rubber-ducky/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rubber Ducky

A built-in critic. Before committing to a non-trivial change, you stop, articulate your current thinking, and have it scrutinized by independent reviewers running on different models than the one driving this session. Unlike a real rubber duck, this one talks back: it returns a structured critique you can act on.

Why this works

Rubber-duck debugging works because articulating your reasoning forces the gaps into view. This version adds two things a desk toy can't:

  1. It talks back. The reviewers return concrete, categorized feedback — not silence.
  2. It doesn't share your blind spots. The reviewers run on the two Claude models you are not using right now, with a clean context. A model that didn't produce the work is far more likely to see what's wrong with it. You get genuinely independent perspectives, not a re-run of the same reasoning that produced the plan.

The single highest-leverage moment is after you've planned a change but before you've written the code. A design flaw caught here costs a paragraph to fix; caught after implementation it costs a rewrite.

rubber-ducky vs /review

Both are read-only critics, but they fire at different stages:

  • rubber-ducky pressure-tests your own in-progress thinking — a plan, a design, an approach, tests you just wrote — usually before or during implementation, using cross-model critics.
  • /review evaluates a finished change — a branch diff or a PR — after the code exists.

Reach for the duck while the decision is still cheap to change; reach for /review when the work is done.

When to consult the duck

Consult it at high-leverage moments, not only when stuck:

  • After planning a non-trivial change, before implementing it. Highest leverage. Corrections are cheapest here.
  • Mid-implementation on complex or multi-file work, to check for blind spots before you're in too deep.
  • After writing tests, to validate the coverage is real and the behavior actually satisfies the original request — not just that the tests pass.
  • Reactively, when you hit repeated failures or unexpected results. Get an independent analysis instead of retrying the same approach a fourth time.
  • Whenever the user explicitly asks ("rubber duck this", "/rubber-ducky", "poke holes in this").

Read the full file on GitHub · 193 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 193 lines · 186 tokens per session scan A d702a89035bc

Subscribe to this mod's changes

rubber-ducky is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 186 tokens to every session and 2,069 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

audit-ppmplugin

Statically audit a built .ppmplugin before wrap testing. Checks archive layout, manifest compatibility, bundle consistency, Android DEX integrity and SDK leakage, iOS framework structure, native source-to-receiver alignment, and the PCF composite-key/sendAsync transport contract. Reports CRITICAL, WARNING, and INFO…

microsoft/power-platform-skills · 112 tokens

debug-extension

Diagnose and fix failures in a built third-party .ppmplugin control: crashes, silent no-ops, PCF error outputs, or incorrect behavior. Uses the reported symptom, shared/error-codes.md, and file-level evidence to trace the manifest, Android/iOS modules, PCF dispatch, and build configuration. Produces a ranked…

microsoft/power-platform-skills · 108 tokens

diagnose-deployment

Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches against a known failure catalog, and optionally auto-fixes identified issues. Use when asked to: "diagnose deployment", "debug deployment", "deployment failed", "show deployment errors", "fix deployment issues", "show upload logs"…

microsoft/power-platform-skills · 82 tokens

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

debug-flow

Debug a failed Power Automate flow run. Use when a flow failed, has errors, or the user wants to troubleshoot a run.

microsoft/power-platform-skills · 30 tokens

investigate

Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.

oliver-kriska/claude-elixir-phoenix · 40 tokens