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/codex-plugin/21st-registrynpx skills add 21st-dev/codex-plugin --skill 21st-registrygit clone --depth 1 https://github.com/21st-dev/codex-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 | $0.00259 | $0.04015 |
| Opus 5 | $0.00130 | $0.02008 |
| Sonnet 5 | $0.00052 | $0.00803 |
| Haiku 4.5 | $0.00026 | $0.00402 |
Grade A, and why
21st-registry 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.
This is a copy
100% identical to 21st-registry — 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.
How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish & manage on the 21st registry
Publish components, themes and templates to 21st.dev, and manage what you've
already published, all through the unified 21st CLI (@21st-dev/cli).
Pre-flight (always)
- Authenticate before publishing. Component publishing, inventory,
checkout, metadata editing, and unpublishing accept either a
21st loginsession or a21st_sk_…API key. Theme/template commands still require a real API key from https://21st.dev/settings/api-keys, passed via--api-key,TWENTYFIRST_TOKEN, orAPI_KEY_21ST. - The CLI is the unified
@21st-dev/cli(bin21st). Don't reinvent — use it. - Search before publishing (
21st search "<query>") so you don't add a duplicate to the library.
Find existing components and drafts
Start here when the user asks to continue or edit old component work:
21st components
21st components --status draft --scope personal --json
21st open component:123
21st open draft:<uuid> --no-open
21st components drains both independently paginated collections by default,
so an unfiltered run returns every accessible personal or Team component and
every owned draft. Narrow it with --status all|draft|published|private or
--scope all|personal|team:<uuid>. Keep the returned stable
component:<id> or draft:<uuid> reference; do not substitute a slug.
21st open draft:<uuid> resumes an editable Studio draft. 21st open component:<id> creates or resumes a server-owned CLI Review revision from the
retained published component code and demos. The live component stays
unchanged until that revision is published. Fresh covers are required, while
optional video generation runs best-effort in the background. --no-open
creates or resumes the workspace and prints its URL without launching a
browser.
Use a local file when the source is already changed:
21st publish ./Component.tsx \
--component component:123 \
--description "What changed"
Never replace the stable ref with a same-slug guess. Only the original component author can check out code. A Team manager can still edit or unpublish a teammate's component metadata by stable ref.
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 · 354 lines · 259 tokens per session scan A b1dd7ca00383
21st-registry is a skill published in the GitHub repository 21st-dev/codex-plugin (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 259 tokens to every session and 4,015 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to 21st-registry, differing in 0 lines, and is treated as a copy.
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…