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 skills/humanerd-drew/opencode-drewgent/baseline-uinpx skills add humanerd-drew/opencode-drewgent --skill baseline-uigit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/baseline-ui)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/baseline-ui"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/baseline-ui.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 | $0.00052 | $0.05565 |
| Opus 5 | $0.00026 | $0.02782 |
| Sonnet 5 | $0.00010 | $0.01113 |
| Haiku 4.5 | $0.00005 | $0.00556 |
Grade A, and why
baseline-ui 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 yesterday.
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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline UI
{{AGENT_NAME}}'s consolidated UI quality bar for all frontend work. Use this on its own or before loading other UI skills.
When to Apply
Reference these guidelines when:
- writing any UI code (HTML, CSS, JS, Svelte, React, Vue)
- reviewing frontend PRs or agent-generated output
- building design tokens or a DESIGN.md
- creating prototypes, landing pages, dashboards, forms, decks
- fixing accessibility or animation issues
- adding SEO/metadata to pages
Rule Categories by Priority
| Priority | Category | Impact |
|---|---|---|
| 1 | Stack Defaults | critical |
| 2 | HTML Semantics | critical |
| 3 | Accessibility | critical |
| 4 | Coherence | critical |
| 5 | Typography | high |
| 6 | Color | high |
| 7 | Layout & Spacing | high |
| 8 | Motion & Animation | medium-high |
| 9 | Interactive Patterns | medium |
| 10 | SEO & Metadata | medium |
| 11 | Content Discipline | medium |
| 12 | Performance | low-medium |
| 13 | Anti-Slop | low |
1. Stack Defaults
- CSS: Modern CSS. Variables for tokens. Grid + Flexbox for layout. Container queries when helpful. Color functions via oklch.
- JS animation:
motion/react(framer-motion rebrand) when JS animation required. CSS animation + transitions preferred otherwise. - Tailwind: Use Tailwind defaults unless custom values already exist or explicitly requested. Prefer
tw-animate-cssfor entrance/micro-animations. - Class utility:
cnutility (clsx+tailwind-merge) for class logic when in a Tailwind project. - Component primitives: Use Base UI / React Aria / Radix for anything with keyboard or focus behavior. MUST use the project's existing primitives first. NEVER mix primitive systems within the same interaction surface. Prefer Base UI for new primitives if compatible with the stack. NEVER rebuild keyboard/focus by hand unless explicitly requested.
- Form elements: Use native
<input type="date">etc. before custom datepickers. - No new dependencies: Follow ponytail checklist before adding any CSS/UI library.
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.
- yesterday First seen · 510 lines · 52 tokens per session scan A 6d3497c19694
baseline-ui is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 5,565 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 2026-09-03.
Other skills, from other repositories
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
emil-design-skills
Use when collection of 8 design engineering skills by Emil Kowalski (Vercel, Linear) — animation standards, UI craft, Apple design principles, library selection, and prototyping. Based on years of production experience. Use when the user asks about UI polish, animation decisions, or wants to audit/improve interface…
reimagine-it
Content-Derived Design — reads existing HTML and writes a stronger standalone page from headings, facts, names, dates, numbers, links, emails, and colors already in that file. CLI: npx reimagine-it --auto -i page.html -o out.html; also variations, lock, and audit. Use when the user says /reimagine-it, "reimagine it"…
web-design
UI review against Web Interface Guidelines. Use when asked to review UI, check accessibility, or audit design.
popular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.
popular-web-designs
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel, Notion, Airbnb, and more. Each template includes colors, typography, components, layout rules, and ready-to-use CSS values.