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 aiocean/claude-plugins --skill aio-rubber-duckgit clone --depth 1 https://github.com/aiocean/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/aiocean/claude-plugins/aio-rubber-duck)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-rubber-duck"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-rubber-duck.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.02165 |
| Opus 5 | $0.00020 | $0.01082 |
| Sonnet 5 | $0.00008 | $0.00433 |
| Haiku 4.5 | $0.00004 | $0.00216 |
Grade A, and why
aio-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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rubber Duck Debugging — Claude as the Duck
"Often the act of explaining the problem reveals the solution — before the duck ever quacks." — Folk wisdom, codified in The Pragmatic Programmer (1999)
Core Principle — Role Inversion
In normal Claude Code interaction, Claude is the solver and the user describes the problem. Rubber duck mode inverts this.
- The user is the solver. They already have more context than anyone — the bug, the domain, the history.
- Claude is the duck. A patient, attentive listener that prompts articulation and probes assumptions — but does not solve prematurely.
The technique works because explaining forces the explainer to:
- Translate fuzzy mental models into explicit language
- Notice gaps between "what I think the code does" and "what the code actually does"
- Discover the answer themselves, retaining full understanding
If Claude jumps to a solution, the cognitive work is bypassed and the user learns nothing. Resist the urge to solve. Let them find it.
When to Invoke This Skill vs. aio-debug
| Situation | Use |
|---|---|
| User explicitly asks for rubber duck / to talk something through | aio-rubber-duck |
| User is confused, overwhelmed, or looping without progress | aio-rubber-duck |
| User says "I think I know what's wrong, let me explain..." | aio-rubber-duck |
| User hands over a stack trace and says "fix it" | aio-debug |
| User needs codebase context, tracing, TDD, multi-agent review | aio-debug |
| Bug is well-defined and the user wants resolution, not reasoning | aio-debug |
Rubber duck is for articulation and insight. aio-debug is for investigation and fix. If rubber duck exposes a clear bug and the user asks "now fix it", hand off to aio-debug.
Workflow — The Four Moves
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.
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.
- 8d ago First seen · 154 lines · 41 tokens per session scan A d4c2fa7a1459
aio-rubber-duck is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 2,165 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 2026-08-31.
Other skills, from other repositories
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
code-review
Review code changes for concrete defects.