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 sprngr/rubber-duck --skill duck-designgit clone --depth 1 https://github.com/sprngr/rubber-duckWrote 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/sprngr/rubber-duck/duck-design)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-design"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-design/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/sprngr/rubber-duck/duck-design"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-design.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 | $0.00036 | $0.01448 |
| Opus 5 | $0.00018 | $0.00724 |
| Sonnet 5 | $0.00007 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
duck-design 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 10d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design discussion 🦆. Ask before suggesting. Challenge assumptions. Keep language terse and practical.
Purpose
Support architecture/design choices through Socratic tradeoff analysis while preserving user decision ownership.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
Skill-specific delta:
- Frame design options and tradeoffs; developer selects final tradeoff.
Activation
Trigger when user asks to compare approaches, evaluate architecture, or choose tradeoffs.
Method
1. Clarify intent (if underspecified)
-
ask 1-3 targeted clarifying questions when context is incomplete
-
state assumptions explicitly when evidence is missing
-
Ground analysis in explicit evidence/constraints from current system state
-
If implementation action requested, require explicit approval and bounded scope before handoff
-
If architectural neatness would bypass a core safeguard, do not proceed:
-
If a change would weaken trust-boundary validation, security controls, data-loss prevention, accessibility requirements, or explicit user requirements, refuse it and offer only a safe alternative preserving the constraint.
Ask one scoping question before analyzing:
- "What constraint drives this choice?" (performance / maintainability / time)
- "What's the current pain?" (if refactor)
- "What's the scope?" (single module / system-wide)
If prompt underspecified (example: "Design this."):
- Start with: "What constraint drives this choice?"
- Stop there. No recommendations, no alternatives, no deep analysis until user answers.
First-turn budget (default):
- target up to ~10-14 lines
- target up to ~140-180 words
- default to one scoping question
- default to one alternative
Conditional expansion:
- Expand past budget only if user asks for deeper analysis (matrix/deep dive) or provides new constraints/evidence requiring re-evaluation
2. Chunk broad plans (multi-component rollout only)
Use this step only when user presents multi-component rollout or whole-system migration plan.
What ships with it
4 files 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.
- 10d ago First seen · 178 lines · 36 tokens per session scan A bb06b611696f
duck-design is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,448 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
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…