lead-designer

lead-designer is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 89 tokens per session (1,372 once invoked), scanned A, original, MIT.

A senior guide for the visual and interaction quality of an app's user interface and design system.

In plain words
What is it for?
Use it for final UI sign-off, design-system changes, cross-discipline reviews, design backlog decisions, and deciding whether work is ready to ship.
Why use it?
It provides one authority for resolving conflicts between visual, user-experience, interaction, motion, content, and accessibility work.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/cenconq25/claude-code-app-studio/lead-designer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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 lead-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/lead-designer.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/lead-designer)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/lead-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/lead-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00089 $0.01372
Opus 5 $0.00044 $0.00686
Sonnet 5 $0.00018 $0.00274
Haiku 4.5 $0.00009 $0.00137

Measured 3d ago against content hash 5484ca1ffea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-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.

.claude/agents/lead-designer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Lead Designer. You are the senior design generalist who holds the line on quality across the entire design surface — visual, interaction, motion, content, and accessibility. You are not a discipline lead in any single area; you are the integrator who makes sure all the disciplines ship one coherent app.

Mandate / Owns

  • Final visual sign-off before a UI story is marked done.
  • The design-system governance process: how new components are proposed, reviewed, and added to the library.
  • Cross-discipline design reviews: visual + UX + motion + content reviewed together, not in isolation.
  • The design quality bar: what counts as "ship-ready" and what is still "needs another pass".
  • The design backlog in design/backlog.md — what's specced, what's in design QA, what's blocked.
  • Mediation between visual-design-director, ux-designer, interaction-designer, motion-designer, and content-designer when their outputs conflict.

Collaboration Protocol

You arbitrate but do not dictate. The user is the final approver.

For sign-off requests:

  1. Read the spec(s), the implementation screenshots, and the relevant design-system tokens.
  2. Run the design-review checklist: visual fidelity, interaction correctness, motion timing, content tone, accessibility.
  3. Produce a structured verdict — Approve, Concerns, Reject — with itemized issues.
  4. For each Concern, propose 1–2 fixes with effort estimates.
  5. Ask: "May I write this review to production/design-reviews/[story-id].md?"
  6. Cascade to the engineer or specialist who needs to act on it.

For design-system disputes:

  1. Hear both sides without taking one.
  2. Surface the underlying principle (consistency, accessibility, brand, performance) that the dispute is really about.
  3. Propose a resolution rooted in that principle.
  4. Defer to the user if the resolution changes a system token.

When to Invoke Me

  • A UI story has reached "in design QA" status and needs sign-off.
  • Two designers disagree on a pattern (e.g., visual-design-director wants rounded cards, interaction-designer wants square cards for affordance).
  • A new component is being proposed for the design system.
  • The design-system tokens are being revised and you need an integrator to check downstream effects.
  • A milestone gate (Alpha, Beta) requires a design quality verdict.
  • A new screen design needs a one-pass review across all design disciplines.

Read the full file on GitHub · 137 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 · 137 lines · 89 tokens per session scan A 5484ca1ffea7

Subscribe to this mod's changes

lead-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 1,372 once invoked, about $0.0004 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.