21st-ai

A terminal-based UI drafting tool creates web interface ideas from prompts, lets you preview and edit versions, and brings the chosen code into your project.

In plain words
What is it for?
It is for sketching UI variants, previewing them in a browser, refining one with plain-language changes, and retrieving its code.
Why use it?
It gives you a quick way to explore interface designs before rebuilding the final version in your project's actual technology stack.

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

Made for: Claude Code, Codex.

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,112 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00195 $0.01112
Opus 5 $0.00097 $0.00556
Sonnet 5 $0.00039 $0.00222
Haiku 4.5 $0.00019 $0.00111

Measured 2d ago against content hash bc928af4cd81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

21st-ai 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

This is a copy

100% identical to 21st-ai — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/21st-ai/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

21st AI — sketch, iterate & grab code from the terminal

21st AI is a fast UI-drafting board. Mental model: draft it here, then finish it — sketch a few variants from a prompt, preview them, refine the one you like with plain-English edits, and pull its code into the repo. The whole loop runs from the 21st CLI (or the matching MCP tools), so you never leave the editor.

Sketch mode produces self-contained HTML + Tailwind drafts (fast, no build). The recommended handoff is the copy-prompt: a spec that tells you to rebuild the design in the target project's real stack — not paste raw HTML verbatim.

Auth

Same credential as the rest of the CLI: 21st login (saved token) or a 21st_sk_ key via --api-key / TWENTYFIRST_TOKEN. 21st usage shows tier + remaining quota. (See the 21st-cli-use skill for the full auth notes.)

The loop

# 1) Sketch — generate variants ("takes") from a prompt. Opens the preview in
#    the browser and prints the projectId.
21st generate "a pricing section with 3 tiers and a monthly/annual toggle"

# 2) List the takes (1-based numbers + whether each has rendered yet).
21st generation <projectId>

# 3) Edit ONE take in place with a natural-language change (PAID — see Metering).
21st iterate <projectId> "make it enterprise-flavored, add an annual toggle" --take 3

# 4) Grab the code to bring into the project (FREE).
21st take <projectId> --take 3            # paste-ready copy-prompt (recommended)
21st take <projectId> --take 3 --code     # raw self-contained HTML instead

Open the preview URL (printed by generate, and returned by iterate) in the editor's built-in browser to watch the variants render and update in place.

When to use which

  • generate — start fresh from a prompt. Returns a preview URL + projectId.
  • generation — list the takes so you know which --take N to act on.
  • iterate — refine an EXISTING take (edited in place; a new version is appended, so you can step back in the workspace). Use this to change something already generated instead of starting over.
  • take — pull a take's code. Default prints the copy-prompt (adapt-to-my- stack spec); --code prints the raw HTML. Both FREE and unlimited.

Read the full file on GitHub · 90 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 · 90 lines · 195 tokens per session scan A bc928af4cd81

Subscribe to this mod's changes

21st-ai is a skill published in the GitHub repository 21st-dev/codex-plugin (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 195 tokens to every session and 1,112 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to 21st-ai, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

mintlify-preview

Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".

latitude-dev/latitude-llm · 69 tokens