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-ainpx skills add 21st-dev/claude-code-plugin --skill 21st-aigit 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 | $0.00195 | $0.01112 |
| Opus 5 | $0.00097 | $0.00556 |
| Sonnet 5 | $0.00039 | $0.00222 |
| Haiku 4.5 | $0.00019 | $0.00111 |
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.
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 Nto 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);
--codeprints the raw HTML. Both FREE and unlimited.
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 · 90 lines · 195 tokens per session scan A bc928af4cd81
21st-ai is a skill published in the GitHub repository 21st-dev/claude-code-plugin (7 stars, last pushed 7d 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. 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…