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/21st-dev/claude-code-plugin/21st-design-syncnpx skills add 21st-dev/claude-code-plugin --skill 21st-design-syncgit clone --depth 1 https://github.com/21st-dev/claude-code-pluginWhat 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 | $0.00129 | $0.01388 |
| Opus 5 | $0.00064 | $0.00694 |
| Sonnet 5 | $0.00026 | $0.00278 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
21st-design-sync 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- 21st-design-sync — 100% identical, 0 lines differ
- 21st-design-sync — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
21st Design Sync — publish your project's design as a theme
Take the design a project already ships (its light + dark CSS variables) and
publish it to the public 21st.dev theme library so anyone can preview,
bookmark, and apply it. Under the hood this is one CLI call:
21st publish-theme <file.css> --name "…".
Pre-flight (always)
- Auth needs a real API key.
publish-themeis a management endpoint: it accepts a21st_sk_…key only, not a21st loginsession token. Get one at https://21st.dev/mcp (or https://21st.dev/settings/api-keys) and pass it via--api-key 21st_sk_…or theTWENTYFIRST_TOKEN/API_KEY_21STenv var. If the user has no key, point them there — don't try to mint one. - The CLI is the unified
@21st-dev/cli(bin21st). Usenpx @21st-dev/cliif it isn't installed. - Publishing is public and outward-facing. A published theme is immediately
is_publicin the community library (there is no unlisted/private option for themes). Confirm with the user before publishing.
Step 1 — Find the project's design tokens
Locate the file that defines the shadcn/Tailwind theme variables. Check, in order:
app/globals.css,src/app/globals.csssrc/index.css,styles/globals.css,app/styles/globals.css
You're looking for a :root { … } block of CSS custom properties
(--background, --foreground, --card, --primary, --secondary,
--muted, --accent, --destructive, --border, --input, --ring, the
--chart-* / --sidebar-* tokens, --radius) and a matching .dark { … }
block. Values may be hsl(...), oklch(...), hex, or raw channels — keep them
exactly as the project wrote them.
Tailwind v4 projects usually keep the same :root / .dark blocks plus an
@theme inline mapping; you only need the :root and .dark token values,
not the @theme mapping.
Step 2 — Assemble a valid theme CSS file
The publish endpoint parses --name: value; pairs out of a :root { … } block
and a .dark { … } block, and requires both to be non-empty. So the file
you publish must contain both.
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.
- 2d ago First seen · 121 lines · 129 tokens per session scan A 65cc94c842e0
21st-design-sync 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 129 tokens to every session and 1,388 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…