design-audit

design-audit is a command for coding agents from adilkalam/orca. It costs 89 tokens per session (1,449 once invoked), scanned A, original, MIT.

A command that reviews interface work for accessibility, speed, behavior on different screen sizes, and common design or code problems. It also reads the project’s product and visual guidance when available.

In plain words
What is it for?
Use it to audit a web interface or SwiftUI screen, including its accessibility, performance, responsive behavior, and adherence to the project’s design rules.
Why use it?
It finds usability and quality issues that may be missed when checking only whether the interface looks correct.

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-audit
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-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/adilkalam/orca/design-audit.svg)](https://agentmods.dev/commands/adilkalam/orca/design-audit)
Your own site
<a href="https://agentmods.dev/commands/adilkalam/orca/design-audit"><img src="https://agentmods.dev/badge/commands/adilkalam/orca/design-audit.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 1,449 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 $0.01449
Opus 5 $0.00044 $0.00724
Sonnet 5 $0.00018 $0.00290
Haiku 4.5 $0.00009 $0.00145

Measured 4d ago against content hash 3d056b2d7a10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-audit 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.

commands/design-audit.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-audit

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 use the Swift detector + iOS banned-rule bullets below; 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. 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("ui-quality-audit") — the ui-quality-audit skill's technical quality checks (a11y, performance, responsive, anti-patterns).

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 audit on the hub's global aesthetic (the banned rules + preferences + voice-anchors still drive the anti-pattern flags) and note once: "No project contract found — auditing against the global aesthetic; run /impeccable --teach to make this project-specific."

Read the global catalog references that matter for audit:

  • ~/.claude/docs/concepts/design-contract/banned/ — the anti-pattern files drive which anti-patterns to flag.
  • ~/.claude/docs/concepts/design-contract/preferences/alignment-precision.md — 7 optical rules + pixel audit are part of the technical-quality pass.

Work

Apply the ui-quality-audit skill's procedures to the user's target. Extend with Adil's aesthetic:

  • Flag every Tailwind palette utility or Tailwind hex value (P0 — banned/colors.md).
  • Flag every reflex-font usage (P0 — banned/fonts.md).
  • Flag every AI-purple / AI-magenta / AI-pink gradient (P0 — banned/gradients.md).
  • Flag every chamfer stack (inset-highlight + outer shadow + gradient on same element; P0 — banned/chamfered-buttons.md).
  • Flag every default-ease transition and bouncy easing (P1 — banned/motion-suddenness.md).
  • Flag every side-stripe border (border-left/border-right > 1px; P0 — banned/chamfered-buttons.md / Bakaus absolute_bans).
  • Flag every gradient text (background-clip: text + gradient; P0 — Bakaus absolute_bans).

Read the full file on GitHub · 71 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. 4d ago First seen · 71 lines · 89 tokens per session scan A 3d056b2d7a10

Subscribe to this mod's changes

design-audit is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,449 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 2026-08-31.