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.
npx agentmods add commands/dammyjay93/interface-design/design-reviewgit clone --depth 1 https://github.com/Dammyjay93/interface-designWrote 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.
[](https://agentmods.dev/commands/dammyjay93/interface-design/design-review)<a href="https://agentmods.dev/commands/dammyjay93/interface-design/design-review"><img src="https://agentmods.dev/badge/commands/dammyjay93/interface-design/design-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.02389 |
| Opus 5 | $0.00020 | $0.01195 |
| Sonnet 5 | $0.00008 | $0.00478 |
| Haiku 4.5 | $0.00004 | $0.00239 |
Grade A, and why
interface-design:design-review 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
An unusually strict review focused on visual craft and hierarchy. The bar is not "does this work" or "does the grid align" — it is "would a design lead at Linear or Apple put their name on this?" Most generated UI is correct (it renders, it aligns, colors don't clash) and not crafted (nothing was decided, the hierarchy is flat, it looks like every other app). This review pulls a build from correct toward crafted, scores what's wrong by how much it matters, and blocks what isn't there yet.
Be ambitious. Don't stop at "this border is a little strong." Look for the decisions that were never made — the defaulted typeface, the absent focal point, the monotone layout — and push for the version that looks designed.
This review judges by default. Report findings and a verdict; only rebuild when the user asks. Keep the review and the mutation cleanly separate.
The Gap: Correct vs Crafted
There's a distance between correct and crafted. Correct means the layout holds and nothing clashes. Crafted means someone cared about every decision down to the last pixel — the way you tell a hand-thrown mug from an injection-molded one. Both hold coffee; one has presence. Generated output lives in correct. Your job is to find every place it defaulted instead of decided, weigh how much each one costs, and name the crafted version.
How to run it
Five steps, in order. Don't skip to the dimension checklist — the procedure is what keeps the review honest and stops it from becoming a list of your personal taste.
Step 1 — Scope and intent
Establish two things:
- What's under review — the current build, a named component, or the branch's UI changes. Bound it.
- What it's trying to be — read
.interface-design/system.mdif it exists, and infer the intended user, task, and feel. You review against the design's own intent, not a generic ideal. A deliberately dense trading terminal is not failing for being dense. If intent is genuinely unknowable, say so and review against general craft — but note the assumption.
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.
- 4d ago First seen · 133 lines · 40 tokens per session scan A dfa72fb49610
interface-design:design-review is a command published in the GitHub repository Dammyjay93/interface-design (5,652 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 2,389 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.
Other commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
template-ui
Design a Sent template-builder interface.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
audit-ux
Whole-repo adversarial UX audit of the shipped user surfaces -> docs/audits/ux-audit- .md.