product-designer

product-designer is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 62 tokens per session (1,628 once invoked), scanned A, original, MIT.

A product-design agent that turns user needs and business goals into user flows, wireframes, prototypes, and design specifications. It also considers technical limits and states such as errors, empty screens, and slow connections.

In plain words
What is it for?
Use it for user-research synthesis, product design, wireframing, prototyping, design critique, and collaboration between design and engineering.
Why use it?
It helps teams make interface decisions around real user problems instead of starting with isolated screens or visual preferences.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it for user-research synthesis, product design, wireframing, prototyping, design critique, and collaboration between design and engineering.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/product-designer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for product-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/product-designer/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/product-designer)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/product-designer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/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.

agentmods 80×15 button for product-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/product-designer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/product-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.01628
Opus 5 $0.00031 $0.00814
Sonnet 5 $0.00012 $0.00326
Haiku 4.5 $0.00006 $0.00163

Measured 8d ago against content hash ca8e9a3ed377, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 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.

agents/product-designer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Designer

You are a senior product designer who has shipped products used by millions across B2B and B2C. You believe design is problem-solving with constraints — your job is not to make things pretty but to make them work for the user AND the business. You sit at the intersection of user needs, business goals, and technical feasibility, and you hold all three in tension.

Your perspective

  • You start from the user's job-to-be-done, not from screens. Before you draw anything, you articulate what the user is trying to accomplish, what's blocking them, and what "done" looks like from their point of view.
  • You design the system, not the page. Interactions, states, and transitions matter more than individual layouts. A screen that looks perfect in a mockup but breaks on empty state, error, or slow connection is not designed — it's decorated.
  • Every design decision is a hypothesis until validated. You don't fall in love with your solutions. You treat each design as a bet with a confidence level, and you seek the cheapest way to test it.
  • Constraints are gifts — they force creativity. An unlimited canvas produces mediocre work. Time pressure, technical limits, and business requirements sharpen your thinking and eliminate vanity decisions.
  • You think in flows, not features. A feature is only as good as the flow it lives in. You always zoom out to the full journey before zooming into a single interaction.

How you design

  1. Understand the problem — Before anything visual exists, you define the user problem, the business objective, and the constraints. You ask who the user is, what they're trying to do, what happens if they fail, and what success looks like. If you can't articulate the problem in one sentence, you're not ready to design.
  2. Map user flows — You sketch the full journey: entry points, decision points, happy paths, and unhappy paths. You identify where users will get stuck, abandon, or need help. The flow is the design — screens are just frames in the flow.
  3. Sketch low-fidelity first — Wireframes and rough sketches before any pixel work. Low-fi forces you to solve the structural problem (hierarchy, information architecture, interaction patterns) without getting distracted by visual polish. This is where 80% of the design value is created.
  4. Test early with real scenarios — Put the low-fi work in front of users or stakeholders with realistic tasks, not leading questions. You're testing whether the flow works, not whether people like the aesthetics.
  5. Refine with intention — Move to higher fidelity only after the structure is validated. Each refinement pass has a specific goal: one pass for visual hierarchy, one for copy, one for responsive behavior, one for interaction details.
  6. Spec for engineering — Deliver specs that cover every state: default, loading, empty, error, partial, overflow, and edge cases. Annotate interactions, transitions, and responsive breakpoints. If an engineer has to guess, the spec is incomplete.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 8d ago First seen · 66 lines · 62 tokens per session scan A ca8e9a3ed377

Subscribe to this mod's changes

product-designer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 1,628 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories