duck-off

duck-off is a command for coding agents from centsandcode/rubber-duck. It costs 8 tokens per session (71 once invoked), scanned A, original, MIT.

A command that turns off Rubber Duck mode, a debugging style that asks guiding questions instead of giving the solution. After it runs, the assistant answers normally and directly.

In plain words
What is it for?
Use it to stop guided, question-based debugging and return to normal answers, including finishing a problem already in progress.
Why use it?
It removes the restriction of receiving only questions while debugging. This is useful when you want the actual explanation, solution, or code.

Command

Part of the rubber-duck plugin — 1 skill, 2 commands 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 commands/centsandcode/rubber-duck/duck-off
Clone the repo
git clone --depth 1 https://github.com/centsandcode/rubber-duck

Or install rubber-duck, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 duck-off

README.md
[![agentmods](https://agentmods.dev/badge/commands/centsandcode/rubber-duck/duck-off.svg)](https://agentmods.dev/commands/centsandcode/rubber-duck/duck-off)
Your own site
<a href="https://agentmods.dev/commands/centsandcode/rubber-duck/duck-off"><img src="https://agentmods.dev/badge/commands/centsandcode/rubber-duck/duck-off.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 71 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 $0.00008 $0.00071
Opus 5 $0.00004 $0.00036
Sonnet 5 $0.00002 $0.00014
Haiku 4.5 $0.00001 $0.00007

Measured 4d ago against content hash 0208f3513fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

duck-off 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.

commands/duck-off.md · 10 lines

What it actually says

Turn OFF Rubber Duck mode. Stop the Socratic questioning.

Answer the user's questions normally and directly from now on, including giving the full solution and code. If the user was mid-problem, give them the answer they were working toward — do not make them ask twice.

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 · 10 lines · 8 tokens per session scan A 0208f3513fe0

Subscribe to this mod's changes

duck-off is a command published in the GitHub repository centsandcode/rubber-duck (15 stars, last pushed 13d ago), licensed MIT. It adds 8 tokens to every session and 71 once invoked, about $0.0000 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.