design-critique

design-critique is a command for coding agents from adilkalam/orca. It costs 63 tokens per session (1,079 once invoked), scanned A, original, MIT.

A command for reviewing a website or app’s user experience, including layout, readability, user expectations, and common design problems.

In plain words
What is it for?
Use it to assess web or SwiftUI screens, identify confusing interactions and visual hierarchy issues, and score design problems against defined rules.
Why use it?
It gives a structured critique instead of relying only on personal opinion. It can use project product and design documents when they exist, while still working without them.

Command

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 commands/adilkalam/orca/design-critique
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca

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-critique

README.md
[![agentmods](https://agentmods.dev/badge/commands/adilkalam/orca/design-critique.svg)](https://agentmods.dev/commands/adilkalam/orca/design-critique)
Your own site
<a href="https://agentmods.dev/commands/adilkalam/orca/design-critique"><img src="https://agentmods.dev/badge/commands/adilkalam/orca/design-critique.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,079 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 5.1 $0.00063 $0.01079
Opus 5 $0.00032 $0.00540
Sonnet 5 $0.00013 $0.00216
Haiku 4.5 $0.00006 $0.00108

Measured 5d ago against content hash 9d799d87a439, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

design-critique 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 5d 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.

commands/design-critique.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-critique

Entry: mandatory skill loading

Target routing (#PATH_DECISION — one rule, not 5 copies): apply ~/.claude/docs/concepts/ios-design-contract/target-routing.md. If the TARGET ends in .swift, load Skill("ios-impeccable-hub") in place of impeccable-hub and run the Swift detector in Assessment B; otherwise keep the CSS/web path unchanged.

Before any work, invoke:

  1. Skill("impeccable-hub") — the aesthetic (felt-state spine + banned rules + preferences + voice-anchors + detector floor). Baseline for every invocation; drives Assessment C (persona red-flags) via its interfaces-that-feel spine. For a .swift target, load Skill("ios-impeccable-hub") instead (SwiftUI banned rules + preferences + the iOS detector contract) — see the routing rule above.
  2. Skill("critique") — the critique skill's review procedure, persona testing, scoring.

Context gathering

Read the current project's .claude/PRODUCT.md (strategic register) and .claude/DESIGN.md (visual contract). If absent, do NOT block — run the critique on the hub's global aesthetic (banned rules + preferences + voice-anchors) and note once: "No project contract found — critiquing against the global aesthetic; run /impeccable --teach to make this project-specific."

Read the global catalog references:

  • ~/.claude/docs/concepts/design-contract/banned/ — the anti-pattern files drive the extended DON'T list.
  • ~/.claude/docs/concepts/design-contract/voice-anchors.md — the aesthetic's heart; inform hierarchy and tone judgments against it.
  • ~/.claude/docs/concepts/design-contract/preferences/ — positive-move catalogs to assess against (what should have been reached for).

Work

Three assessments in order:

Assessment A — LLM review (from the critique skill). Visual hierarchy, information architecture, emotional resonance, cognitive load. Apply Bakaus's extended DON'T list AND Adil's refusals catalog (the banned rules). Cite specific banned-rule files when flagging issues.

Read the full file on GitHub · 58 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. 5d ago First seen · 58 lines · 63 tokens per session scan A 9d799d87a439

Subscribe to this mod's changes

design-critique is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,079 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 2026-08-31.