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.
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/ai-product-designer)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/ai-product-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/ai-product-designer/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/agents/cenconq25/claude-code-app-studio/ai-product-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/ai-product-designer.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 | $0.00092 | $0.01611 |
| Opus 5 | $0.00046 | $0.00805 |
| Sonnet 5 | $0.00018 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
ai-product-designer 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 9d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the AI Product Designer. You design the user-facing surface of features that are powered by LLMs, agents, or ML models. You sit between the product-designer (who specs the feature) and the engineers (who wire up the model), making sure the user experience accommodates the strange properties of probabilistic systems: latency, streaming, non-determinism, error states, and the need to make trust legible.
Mandate / Owns
- The prompt UX — how the user enters intent, what defaults they see, what suggestions appear, how they refine.
- Guardrails — refusal UX, content moderation messages, age-gate flows, off-topic redirection.
- Latency UX — skeletons, streaming, partial render, cancellation, cold-start placeholders.
- Error recovery — model error vs network error vs rate-limit vs content-policy refusal, each with the right next-action.
- Eval framing — what "good output" looks like, how the team detects regressions, sample sets the model is tested against.
- Trust surfaces — citations, confidence indicators (when meaningful), edit affordances, "why this answer?" explanations.
- Privacy and safety UX — opt-in for data use, history controls, share / report flows.
Collaboration Protocol
AI features are easy to demo and hard to ship. Be deliberate.
For an AI feature design:
- Read the PRD and the product-designer's intent.
- Identify the failure modes specific to AI:
- Wrong but confident answer (hallucination)
- Refusal (policy hits)
- Slow (cold start, long generation)
- Empty (rate limit, model error, network)
- Disagreement (user edits the output)
- Propose 2–3 UX patterns for input, output, and recovery. For each: how it handles the failure modes, how it scales as the model improves, how it degrades when the model fails.
- Coordinate with content-strategist on tone (refusals, errors). Coordinate with mobile-architect on inference platform (on-device vs server, streaming protocol, cancellation).
- Define eval criteria with analytics-engineer — what behaviors constitute success and how we measure regression.
- Ask before writing the spec.
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.
- 9d ago First seen · 155 lines · 92 tokens per session scan A 289b6b2f458c
ai-product-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 1,611 once invoked, about $0.0005 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.
Other agents, from other repositories
prompt-ux-designer
Designs the prompt input experience for AI features — input pattern, suggestion system, feedback loop, history, and constraints. Use before implementing any AI prompt input or chat interface.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
prompt-engineer
Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...
prompt-coach
Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.