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 RBraga01/builder-design --skill prompt-ux-designgit clone --depth 1 https://github.com/RBraga01/builder-designWrote 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/rbraga01/builder-design/prompt-ux-design)<a href="https://agentmods.dev/skills/rbraga01/builder-design/prompt-ux-design"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/prompt-ux-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/rbraga01/builder-design/prompt-ux-design"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-design/prompt-ux-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 | $0.00041 | $0.01443 |
| Opus 5 | $0.00020 | $0.00722 |
| Sonnet 5 | $0.00008 | $0.00289 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
prompt-ux-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 12d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt UX Design
The Law
THE PROMPT INPUT IS THE PRODUCT INTERFACE FOR AN AI FEATURE.
"It's just a text box" ships an input with no suggestions, no state feedback, and no token limit — users probe the model by trial and error until they give up.
Input design + suggestion system + 6-state feedback loop + constraints IS a prompt UX.
When to Use
Trigger when:
- Designing the user-facing input for any AI feature
- Adding a chat or conversational interface
- Designing inline AI suggestions (autocomplete, copilot-style)
- Designing an agent invocation interface (slash commands, @ mentions)
- Reviewing whether an existing prompt input meets production standards
When NOT to Use
- API-only interfaces with no user-facing input
- Admin / developer tools where power users are the only audience (simplify; don't over-design)
The Five Prompt UX Dimensions
1 — Input Design
The physical input must match the expected interaction pattern:
| Pattern | Use When | Input Type |
|---|---|---|
| Short query | Single-question answers, search | Single-line input, auto-submit on Enter |
| Multi-line | Document drafting, detailed prompts | Auto-resize textarea, Cmd+Enter to send |
| Conversational | Chat, back-and-forth dialogue | Textarea + history above |
| Command | Agent invocation, slash commands | Input with @ / / trigger detection |
| Constrained | Structured data entry, forms | Templated input with field hints |
Never default to multi-line when single-line is appropriate. Never use a fixed-height textarea.
2 — Suggestion System
Users don't know what the model is good at. Suggestions teach the interaction model.
Types:
- Example prompts — shown in the empty state; clickable, task-specific
- Autocomplete suggestions — appear as the user types (ghost text or dropdown)
- Refinement suggestions — shown after a response ("Try asking: follow-up 1 / follow-up 2")
- Slash commands —
/summarise,/translate,/explain— explicit capability menu
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.
- 12d ago First seen · 144 lines · 41 tokens per session scan A 4521256202c1
prompt-ux-design is a skill published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,443 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
ai-product-design
Design, specify, map, evaluate, or improve an AI assistant, LLM feature, copilot, chatbot, agent, recommendation, generation, or automation workflow. Define capability boundaries, user control, recovery, trust, evidence, uncertainty, permissions, and evaluation. Trigger on "design this AI feature", "build an AI…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…