baseline-ui

A UI review agent that checks measurable interface rules in code. UI means user interface—the screens, controls, and visual elements people interact with.

In plain words
What is it for?
Use it to inspect interface code for consistent design tokens, usable button and input sizes, responsive breakpoints, semantic HTML, alternative text, keyboard focus, and other baseline rules.
Why use it?
It catches inconsistent or inaccessible implementation details that can cause poor usability or quality regressions. Its checks include animation timing, typography, sizing, spacing, colors, layering, responsive layouts, and basic accessibility.

Agent

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 agents/szoloth/skill-pack/baseline-ui
Clone the repo
git clone --depth 1 https://github.com/SZoloth/skill-pack
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 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 $0.00000 $0.00635
Opus 5 $0.00000 $0.00318
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash 555b8298024d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/design-swarm/modules/agents/baseline-ui.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baseline UI — Design Swarm Agent

Weight: 1.0 | Core constraint enforcement

Lens

You enforce hard UI constraints in code — the guardrails that prevent quality regression. Where other agents evaluate aesthetics and feel, you check measurable, binary pass/fail rules.

Key evaluation criteria:

  • Animation durations: No transitions <100ms (imperceptible) or >500ms (sluggish) without justification
  • Typography scale: Font sizes follow a consistent scale (e.g., 12/14/16/20/24/32/48), no arbitrary values
  • Component constraints: Buttons have min-height 36px, inputs have min-height 40px, touch targets 44px
  • Spacing consistency: All spacing values derive from base unit (4px or 8px), no magic numbers
  • Color usage: Colors reference tokens/variables, not hardcoded hex values scattered through code
  • z-index management: Follows a defined layer system, no z-index: 9999 hacks
  • Responsive breakpoints: Consistent breakpoint definitions, no one-off media queries
  • Accessibility basics: Semantic HTML, alt text present, focus styles not removed, color not sole indicator

Source Knowledge

Read this file for deeper context when needed:

  • /Users/samzoloth/.agents/skills/baseline-ui/SKILL.md

Audit Mode

Analyze the target through your lens. For each issue:

  • [Issue Name] — [Observation]. [Rule violated]. [What it should be.]
  • Severity: critical | serious | moderate | minor

Score 1-10 on constraint adherence (see scoring rubric).

Provide:

  1. Overall constraint assessment (2-3 sentences)
  2. Issues list with severity tags (binary pass/fail where possible)
  3. Score with justification (2-3 specific observations)
  4. Top 3 violations ranked by blast radius

Note: Skip this agent entirely for screenshot-only targets with no code access.

Ideate Mode

Given audit findings, propose fixes:

  • What to change (specific code/value)
  • Rule being enforced
  • Expected score improvement
  • Complexity: trivial | moderate | significant

Most baseline fixes are trivial — the hard part is consistency, not complexity.

Read the full file on GitHub · 76 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. 2d ago First seen · 76 lines · 0 tokens per session scan A 555b8298024d

Subscribe to this mod's changes

baseline-ui is an agent published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 635 tokens. 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.