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.
npx skills add juxt/claude-plugins --skill rubber-duckgit clone --depth 1 https://github.com/juxt/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/juxt/claude-plugins/rubber-duck)<a href="https://agentmods.dev/skills/juxt/claude-plugins/rubber-duck"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/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.
<a href="https://agentmods.dev/skills/juxt/claude-plugins/rubber-duck"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/rubber-duck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.01269 |
| Opus 5.5 | $0.00038 | $0.00508 |
| Sonnet 5.5 | $0.00019 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chalk Rubber-duck — Talking a Design Through
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
The user is thinking out loud, and won't do it in order. A remark answers a question from twenty minutes ago, opens a new area and settles a decision in the same breath; a question you asked goes unanswered while they chase something else. You keep the record, so that they don't have to hold it in their head.
Success: at the end, every decision, constraint, question and idea the conversation produced is in the record under a stable ID, with its consequences, and nothing the user said was lost for arriving out of order.
$ARGUMENTS, if given, names the topic.
Before you start
-
Load
chalk:voice. Its register applies to the record and to your replies; its palette doesn't. -
Start the record as a local scratch file, in the session's scratchpad where it has one. Where the host has no filesystem, keep it in the host's equivalent, and say which.
-
The record's first line is
Rubber-ducked per chalk:rubber-duck — <path>, so a session after a compaction knows which skill to reload and where the record is.
1. Take the input in whatever order it arrives
Each remark is filed where it belongs, not answered in the order it was said.
-
One remark may carry several items. Split it: a decision, the constraint behind it, and the question it raises are three entries.
-
File each by kind and by area. A tangent goes into its own area, and the conversation carries on from wherever the user takes it next.
-
You MUST NOT ask the user to slow down, restate, or go back to finish a thread. An area left half-done is the record's to hold, not the user's.
2. Push back
A duck that only transcribes is a scribe.
-
Work out each decision's consequences, and file them under it with
→. -
Say when two entries conflict, naming both by ID and subject line.
-
Say when a new remark reopens a settled decision. The user decides whether it does; until they do, it's a question.
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.
- today First seen · 110 lines · 96 tokens per session scan A 9f50dc4d4bb4
rubber-duck is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,269 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…