21st-ui-explore

A UI exploration workflow creates and compares several substantially different interface directions while keeping the project's design system, technology, content, and accessibility requirements. A design system is the shared set of visual and interaction rules used by a product.

In plain words
What is it for?
It is for redesign concepts, visual experiments, layout alternatives, navigation choices, and selecting a direction for a new interface.
Why use it?
It helps when the desired interface is unclear by turning broad design ideas into comparable options with explicit tradeoffs.

Skill for Claude CodeCodex

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 skills/21st-dev/claude-code-plugin/21st-ui-explore
Any agent
npx skills add 21st-dev/claude-code-plugin --skill 21st-ui-explore
Clone the repo
git clone --depth 1 https://github.com/21st-dev/claude-code-plugin

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 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 $0.00098 $0.00450
Opus 5 $0.00049 $0.00225
Sonnet 5 $0.00020 $0.00090
Haiku 4.5 $0.00010 $0.00045

Measured 2d ago against content hash 4482d001cfe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

21st-ui-explore 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

plugins/21st/skills/21st-ui-explore/SKILL.md · 52 lines

What it actually says

Explore grounded UI directions

Create real choices without abandoning the project's visual identity.

Workflow

  1. Read .21st/design.json and the relevant product UI. If context is missing, run 21st init --design-context.

  2. Search 21st for multiple relevant references before generating:

    21st search "<interface and product context>" --context auto
    
  3. Define three named directions. Each direction must differ on at least two meaningful axes such as hierarchy, information density, navigation model, content emphasis, interaction pattern, or composition. Color-only variants do not count.

  4. Keep shared constraints fixed: real stack, tokens, brand assets, required content, accessibility, and responsive behavior.

  5. Generate or implement comparable previews. Prefer:

    21st generate "<goal plus fixed constraints>" --context auto --variants 3
    
  6. Present the options together when the host supports a picker. Otherwise give each option a preview/deep link and a compact comparison.

  7. Recommend one direction with concrete tradeoffs, but let the user choose.

  8. After selection, remove abandoned local variants and record the decision in .21st/design.json.

Direction contract

For every direction provide:

  • a short, descriptive name;
  • the core idea and intended user effect;
  • the 21st/project references used;
  • what stays consistent with the project;
  • two or more meaningful differences;
  • accessibility or responsive risks;
  • the best-fit scenario.

Do not generate random style mutations. Every difference must support a product or usability hypothesis that a user can evaluate.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 52 lines · 98 tokens per session scan A 4482d001cfe8

Subscribe to this mod's changes

21st-ui-explore is a skill published in the GitHub repository 21st-dev/claude-code-plugin (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 98 tokens to every session and 450 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens