Borrowing it
Nothing to install: this file belongs to ra3orblade/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ra3orblade/swarm/main/.claude/skills/design-review/SKILL.mdgit clone --depth 1 https://github.com/ra3orblade/swarmWrote 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/skills/ra3orblade/swarm/design-review)<a href="https://agentmods.dev/skills/ra3orblade/swarm/design-review"><img src="https://agentmods.dev/badge/skills/ra3orblade/swarm/design-review/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.
<a href="https://agentmods.dev/skills/ra3orblade/swarm/design-review"><img src="https://agentmods.dev/badge/skills/ra3orblade/swarm/design-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00040 | $0.00389 |
| Opus 5 | $0.00020 | $0.00195 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
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 10d 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.
What it actually says
Design review
For changes under packages/web. Report findings; don't edit unless asked. Where possible, load the running dashboard in the browser (swarm ui / the daemon URL) and screenshot the affected view to check it for real.
Checklist
- Theme tokens only — colors/space via CSS custom properties (
--acc,--panel, …); no hardcoded hex in new rules. Every color must resolve in both light and dark (testdata-themeandprefers-color-scheme); no color defined only inside a media/[data-theme]block. - Brand — accent is grass-green/lime; the pixel mark stays crisp (
image-rendering: pixelated); icons match the set already in use. - Layout — no horizontal body scroll; wide tables/charts scroll inside their own
overflow-x:auto; relative units; the view holds up narrow. - Legibility — numbers tabular-aligned; truncation has a
title; empty/loading/error states exist; status uses the established dot/badge vocabulary. - Interaction & a11y — keyboardable (focus states,
esc/nav); destructive actions (force-release, delete) need a typed confirm; live updates don't steal scroll position. - Truth — the dashboard never shows state the CLI/
/v1API can't; no invented data.
Output
A ranked list of concrete issues (what, where, why it matters), most-impactful first, with a screenshot when you captured one. Note what's good briefly, then the fixes.
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.
- 10d ago First seen · 20 lines · 40 tokens per session scan A 311b00f8c6d0
design-review is a skill published in the GitHub repository ra3orblade/swarm (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 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 2026-08-31.
Other skills, from other repositories
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
real-prototype
Implement several variations of a design directly inside the running app, on the real page/route, with a live switcher to toggle between them in the browser, then recommend one and fold the winner into the real code. Variants are real implementations judged against real data, layout, and density (not an isolated…
remove-ai-slop
Audit UI, docs, or prose for AI-generated tells in design and copy, then fix approved findings. Use when the user says de-slop, slop check, "looks AI-generated", or wants copy humanized.
create-design-system
You are an expert design systems architect.
excalidraw-diagram
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts. Generates .excalidraw JSON and renders to PNG for validation.
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.