critique-screen

critique-screen is a command for Claude Code from Owl-Listener/designer-skills. It costs 16 tokens per session (441 once invoked), scanned A, original, MIT.

A command that runs seven reviews of a screen, covering visual hierarchy, brand consistency, composition, typography, colour, affordances, and information density. Affordances are the visual clues that show what people can interact with.

In plain words
What is it for?
Use it for a full screen audit before release or during design review, with fixes ranked by urgency.
Why use it?
It combines visual and usability findings into one prioritised list. This helps teams find problems affecting accessibility, task completion, clarity, or brand compliance.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the visual-critique plugin — 7 skills, 2 commands shipped together

Good fit Use it for a full screen audit before release or during design review, with fixes ranked by urgency.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/owl-listener/designer-skills/critique-screen
About the project

Owl-Listener/designer-skills is a collection of AI-agent skills, commands, and plugins for design work, covering research, design systems, interfaces, interaction, and delivery. Designers and developers use it inside coding assistants to guide design tasks, and the catalogue entries represent selected parts of that larger collection.

Owl-Listener/designer-skills · 2,593 stars · on GitHub

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/Owl-Listener/designer-skills

Made for: Claude Code.

Or install visual-critique, the plugin that ships this one along with the rest of its 7 skills, 2 commands.

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 critique-screen

README.md
[![agentmods](https://agentmods.dev/badge/commands/owl-listener/designer-skills/critique-screen/github.svg)](https://agentmods.dev/commands/owl-listener/designer-skills/critique-screen)
Your own site
<a href="https://agentmods.dev/commands/owl-listener/designer-skills/critique-screen"><img src="https://agentmods.dev/badge/commands/owl-listener/designer-skills/critique-screen/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 critique-screen

Your own site · 80×15
<a href="https://agentmods.dev/commands/owl-listener/designer-skills/critique-screen"><img src="https://agentmods.dev/badge/commands/owl-listener/designer-skills/critique-screen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 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 $0.00016 $0.00441
Opus 5 $0.00008 $0.00220
Sonnet 5 $0.00003 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 7d ago against content hash d15d47a9ab02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

critique-screen 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 7d 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.

visual-critique/commands/critique-screen.md · 25 lines

What it actually says

/critique-screen

Run a full visual critique of a screen across hierarchy, brand, composition, typography, colour, affordance, and information density.

Steps

  1. Visual hierarchy — Analyse entry point, eye flow, weight, and emphasis using critique-visual-hierarchy skill.
  2. Brand consistency — Check mood, voice, and token alignment using critique-brand-consistency skill.
  3. Composition — Evaluate balance, whitespace, rhythm, and gestalt using critique-composition skill.
  4. Typography — Audit scale, readability, consistency, and token compliance using critique-typography skill.
  5. Colour — Audit contrast ratios, palette coherence, semantic colour use, and accessibility using critique-color skill.
  6. Affordance — Evaluate clickability signals, state visibility, CTA clarity, and action discoverability using critique-affordance skill.
  7. Information density — Assess cognitive load, content priority, scanning patterns, and progressive disclosure using critique-information-density skill.
  8. Prioritise — Collect every flagged issue from all seven critiques and rank them:
    • P1 — Critical: Breaks usability, accessibility, or brand compliance; fix before shipping.
    • P2 — Important: Degrades experience or creates inconsistency; fix in current sprint.
    • P3 — Polish: Minor visual refinement; address when capacity allows.

Output

A single prioritised fix list grouped by priority level. Each item includes:

  • Issue: what is wrong
  • Dimension: which critique area it belongs to (Hierarchy / Brand / Composition / Typography / Colour / Affordance / Density)
  • Fix: the specific change required Conclude with a one-paragraph overall assessment noting the strongest and weakest dimension.
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. 7d ago First seen · 25 lines · 16 tokens per session scan A d15d47a9ab02

Subscribe to this mod's changes

critique-screen is a command published in the GitHub repository Owl-Listener/designer-skills (2,593 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 441 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 2026-09-03.