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.
git clone --depth 1 https://github.com/app-builders-club/design-builderWrote 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/app-builders-club/design-builder/review)<a href="https://agentmods.dev/commands/app-builders-club/design-builder/review"><img src="https://agentmods.dev/badge/commands/app-builders-club/design-builder/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/commands/app-builders-club/design-builder/review"><img src="https://agentmods.dev/badge/commands/app-builders-club/design-builder/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 | $0.00036 | $0.01412 |
| Opus 5 | $0.00018 | $0.00706 |
| Sonnet 5 | $0.00007 | $0.00282 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-builder:review — strict design critique
You audit a piece of design and produce a P0-P3 report with actionable findings. You do NOT fix anything (that's /improve's job).
Activate the design skill (skills/design/SKILL.md).
Phase 1 — Determine input mode
Parse the argument:
- Figma URL (host is
figma.com) → mode =visual(Figma). - HTTP(S) URL or comma-separated URL list (e.g.
http://localhost:3000,https://example.com,https://example.com/pricing) → mode =visual(auto-capture). Pass the URLs through to the auditor asurls; the auditor invokesplaywright-cliperskills/playwright-cli/SKILL.mdand populatesdesign/screenshots/as a side effect. screenshots(literal) or path underdesign/screenshots/→ mode =visual(screenshots).- File path / directory / empty → check if visual is available:
design/screenshots/has files matching the target → mode =mixed.- No visual → mode =
code_only.
Capture the chosen mode for the report.
Phase 2 — Delegate to design-auditor
Before dispatching, read the project's three foundation files so the auditor has correct context:
design/design-system.md— design intent, direction, token decisionsdesign/style-guide.md— typography scale, color palette, spacing, accessibility floor (contrast table)design/content-library.md— voice & tone principles, copy patterns
Use the Task tool to invoke the design-auditor sub-agent (see agents/design-auditor.md). Pass:
project_path— the resolved target rootplatform—web/ios/cross(infer from project: SwiftUI present → ios; tailwind/React → web; both → cross)mode—visual/code_only/mixed(from Phase 1)scope— glob if user narrowed (e.g.src/pages/landing.tsx)figma_url— if applicablescreenshot_paths— list of screenshot files if applicableurls— list of HTTP(S) URLs to auto-capture via playwright-cli, if Phase 1 resolved a URL argumentviewports— defaults to["1440x900", "375x812"]; pass through if the user overrode it
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.
- 9d ago First seen · 73 lines · 36 tokens per session scan A 44394c8c3e9a
review is a command published in the GitHub repository app-builders-club/design-builder (4 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,412 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 commands, from other repositories
octo-design-ui-ux
Design UI/UX systems with style guides, palettes, typography, and component specs.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
figma-component-library
Generate a complete component library in Figma from a design system config — atoms, molecules, and organisms with all variants, auto layout, and component properties.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.