design-critic

design-critic is an agent for Claude Code from recomposesh/recompose. It costs 41 tokens per session (236 once invoked), scanned A, original, MIT.

A review agent for checking the visual and interaction quality of a user-interface change. It compares screenshots and code with a project's design system and macOS conventions.

In plain words
What is it for?
Use it to review affected screens or components, rank design fixes by impact, and connect each issue to a screenshot and relevant design rule.
Why use it?
It helps identify layout, hierarchy, and interaction problems that may be missed during implementation.

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/recomposesh/recompose/design-critic
Clone the repo
git clone --depth 1 https://github.com/recomposesh/recompose

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 design-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/recomposesh/recompose/design-critic.svg)](https://agentmods.dev/agents/recomposesh/recompose/design-critic)
Your own site
<a href="https://agentmods.dev/agents/recomposesh/recompose/design-critic"><img src="https://agentmods.dev/badge/agents/recomposesh/recompose/design-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 236 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 $0.00041 $0.00236
Opus 5 $0.00020 $0.00118
Sonnet 5 $0.00008 $0.00047
Haiku 4.5 $0.00004 $0.00024

Measured 4d ago against content hash bf13ac1cdc67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-critic 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 4d 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/design-critic.md · 19 lines

What it actually says

You judge the visual and interaction quality of a UI change. You inspect screenshots and the component code, and you change nothing.

Expect the screenshots, the design intent, and the affected screens or components. The design-system-patterns and macos-design-guidelines skills carry the token rules and the platform conventions. Project memory holds the recurring critiques worth another pass.

Return fixes ranked by impact. For each fix, name the screen, the problem, and the design principle it breaks. Point to the design system token or macOS convention that resolves it. Reference a screenshot region so the reader can see the issue.

When the design intent is missing or the mockup and the build disagree, report back rather than assume. Never approve a screen on taste alone.

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. 4d ago First seen · 19 lines · 41 tokens per session scan A bf13ac1cdc67

Subscribe to this mod's changes

design-critic is an agent published in the GitHub repository recomposesh/recompose (27 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 236 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 2026-08-30.