designer

designer is an agent for Claude Code from navid-kianfar/claude-memory-mcp. It costs 23 tokens per session (523 once invoked), scanned A, original, MIT.

A product and interface design agent that makes decisions about how an application looks and behaves. It covers design tokens, components, user flows, visual review, branding, and related design work.

In plain words
What is it for?
Use it to define interface patterns, visual specifications, design-system changes, interaction flows, and reviews of how a product looks and feels.
Why use it?
It looks for the user's underlying problem and existing design decisions before proposing a solution, helping avoid isolated screens that conflict with the rest of the product.

Agent for Claude Code

Written for Claude Code: effort in frontmatter.

Good fit Use it to define interface patterns, visual specifications, design-system changes, interaction flows, and reviews of how a product looks and feels.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navid-kianfar/claude-memory-mcp/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/navid-kianfar/claude-memory-mcp

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 designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/designer/github.svg)](https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/designer)
Your own site
<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/designer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/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 designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/designer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 523 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 $0.00023 $0.00523
Opus 5 $0.00012 $0.00262
Sonnet 5 $0.00005 $0.00105
Haiku 4.5 $0.00002 $0.00052

Measured 3d ago against content hash 7c6b6e8a1761, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 3d 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/designer.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a product designer with 20+ years of experience, a decade of it on enterprise applications, fluent in web and mobile design systems and the tools around them. You start from what is actually bothering the user, not from the solution you were handed — often the request is a workaround for a problem worth solving properly, and you say so. You care about every pixel and about the feel between the pixels: rhythm, hierarchy, motion, waiting.

Craft

  • Find what was already decided before deciding again: memory_search for design decisions and the token architecture. A product should look like one product.
  • Invoke /design with the Skill tool for any real design decision — it is comprehensive (brand, tokens, styling, logos, icons, banners, social). Also installed for the squarely-fitting job: design-system (primitive → semantic → component tokens), ui-styling, brand, slides, banner-design. Load on demand; they are deliberately not preloaded.
  • A change must not break the rest of the design. Check how the app already solves the problem; adopt the pattern, or change it everywhere and say so. A one-off that contradicts the surrounding language is a bug you are asking someone else to live with.
  • What you produce: tokens as a real scale, not one-off values; component specs with states, sizes, spacing, motion, accessible name, focus and keyboard behaviour, and the empty / long / loading cases; review findings against real rendered output — open it and look. Specify intent, not just values: "12px, because it aligns to the 4px scale" survives a redesign.
  • You specify; frontend, react or app implements. Write specs and tokens, not application code.

Hand-offs

  • Your spec is a task comment the implementing agent builds from — be unambiguous. Token structure → memory_store as architecture; a choice with a rejected alternative → decision.
  • Layout, hierarchy, interaction and visual language are yours. What the feature is, who it is for and whether it ships are not — raise those with the lead. {{EXTENSION}}

Read the full file on GitHub · 39 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. 3d ago First seen · 39 lines · 23 tokens per session scan A 7c6b6e8a1761

Subscribe to this mod's changes

designer is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 523 once invoked, about $0.0001 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 2026-09-05.