What is 21st-cli-use?

A command-line tool for finding, installing, viewing, and generating React and shadcn interface components, themes, and templates from 21st.dev.

Use it to search the 21st.dev catalogue, inspect or install components and themes, and generate new components when needed.

It reduces the need to build common interface pieces from scratch when a suitable catalogue item exists.

21st-cli-use — Skill by 21st-dev

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-cli-use

Any agent

npx skills add 21st-dev/claude-code-plugin --skill 21st-cli-use

Clone the repo

git clone --depth 1 https://github.com/21st-dev/claude-code-plugin

Made for: Claude Code, Codex.

Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,203 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00160	$0.01203
Opus 5	$0.00080	$0.00602
Sonnet 5	$0.00032	$0.00241
Haiku 4.5	$0.00016	$0.00120

Measured yesterday against content hash c888765e0640, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

21st-cli-use scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Prints each logo's name and SVG url(s) to curl straight into a project. Uses the

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

21st-cli-use — 100% identical, 0 lines differ
21st-cli-use — 100% identical, 0 lines differ

plugins/21st/skills/21st-cli-use/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

21st CLI — find, install & generate from the terminal

The 21st CLI (npx @21st-dev/cli, bin 21st) is the command-line surface for the 21st.dev catalog. Search first, install what fits, and only hand-write UI when nothing matches. To publish your own components/themes/templates, use the 21st-registry skill; to publish a project's design as a theme, use 21st-design-sync.

Auth (do this once)

Two interchangeable credentials, both sent as the API key:

Login session — npx @21st-dev/cli login opens the browser and saves a token to ~/.config/21st/auth.json. Best for interactive/dev machines.
API key — 21st_sk_… from https://21st.dev/mcp (or https://21st.dev/settings/api-keys). Pass via --api-key <key> or the TWENTYFIRST_TOKEN / API_KEY_21ST env var. Best for CI.

21st whoami shows the signed-in account; 21st usage shows tier + remaining free quota; 21st logout clears the saved login.

Metering

Metadata (search, previews, a theme's CSS) is free. Retrieving component code (21st get, install) and AI generation are metered per user: a small free daily quota, then a paywall (21st usage shows what's left). Community access / membership lifts the quota.

Find

# Search everything (components + themes + templates)
21st search "pricing table" --limit 10
21st search button --type c        # components only (c | theme | template)
21st search dark --type theme
# Filters: --tag <slug> --color <bucket> --sort <s> --free|--paid
#          --author <username> --mine --liked   --json for machine output

Always search before hand-writing a component — a close match is usually faster to install and adapt than to build from scratch.

Logos

21st logo discord            # search brand + UI SVG logos (free, no login)
21st logo "next js" --limit 5 --json

Prints each logo's name and SVG url(s) to curl straight into a project. Uses the open svgl.app library; free and unmetered on every plan.

Read the full file on GitHub · 122 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.

yesterday First seen · 122 lines · 160 tokens per session scan A c888765e0640

Subscribe to this mod's changes

21st-cli-use 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 160 tokens to every session and 1,203 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Frontend Research

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

21st-cli-use