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 skills add J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill 21st-dev-componentsgit clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-SuiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/21st-dev-components)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/21st-dev-components"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/21st-dev-components/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/21st-dev-components"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/21st-dev-components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00097 | $0.02054 |
| Opus 5 | $0.00048 | $0.01027 |
| Sonnet 5 | $0.00019 | $0.00411 |
| Haiku 4.5 | $0.00010 | $0.00205 |
Grade A, and why
21st-dev-components 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 6d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
21st.dev Reference-to-Component Skill
This skill routes between two flows:
- Auto mode: the user provides a reference site URL and wants the agent to inspect it, infer the required sections, choose matching 21st.dev components automatically, and integrate them.
- Manual mode: the user wants guided collection. The agent lists the sections, tells the user what to fetch from 21st.dev, then integrates the returned handoff.
Use this skill only for React-family projects. If the repo is not React-based, explain that v1 of this skill is React-only and stop.
Bundled Resources
references/categories.mdUse for section-to-category mapping and direct 21st.dev category URLs.references/manual-handoff-template.mdUse when the user is gathering components manually.references/section-detection-rubric.mdUse during Auto mode after crawling the reference site.scripts/resolve-21st-component.mjsResolve a 21st.dev component page into normalized metadata.scripts/fetch-21st-source.mjsFetch raw source from 21st CDN URLs.scripts/build-manual-handoff-template.mjsGenerate a manual handoff markdown file for the user.
Raw Code Resolution Standard
Do not derive 21st.dev CDN source URLs by string concatenation or by manually modifying the community page URL.
Always treat the user-facing 21st.dev component page as the source of truth, then resolve it into metadata before fetching code.
Required workflow
- Start with the 21st.dev community component URL.
- Run the resolver script on that page URL.
- Read
codeUrlanddemoCodeUrlfrom the resolver output. - Fetch source from those returned URLs.
- Only fall back to manual copy/paste if resolution succeeds but raw source cannot be fetched in the current environment.
Command
node scripts/resolve-21st-component.mjs --url "<21st-component-url>" --json
Why this rule exists
21st.dev community URLs do not always map cleanly to CDN paths. Mismatches can include:
- author slug differences between page URL and CDN path
- internal user IDs in CDN paths instead of public author names
- timestamped filenames such as
code.1748367465506.tsx - version query params such as
?v=1 - demo paths that are not reliably predictable
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- 21st-handoff.md 2.0 KB
- references/categories.md 4.9 KB
- references/manual-handoff-template.md 1.6 KB
- references/section-detection-rubric.md 2.3 KB
- scripts/_shared.mjs 11 KB runs code
- scripts/build-manual-handoff-template.mjs 2.5 KB runs code
- scripts/fetch-21st-source.mjs 1.7 KB runs code
- scripts/resolve-21st-component.mjs 4.3 KB runs code
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.
- 6d ago First seen · 245 lines · 97 tokens per session scan A 5f436ecb9482
21st-dev-components is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed 4d ago), licensed ISC. It adds 97 tokens to every session and 2,054 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. Use when building complex…
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
liquid-metal-border
Add and tune animated liquid-metal WebGL borders with the React metal-fx package. Use when buttons, icon controls, chips, tabs, cards, or selected surfaces need a metallic active, selected, hover, focus, or premium border; when implementing the MetalFx component from metal.jakubantalik.com; or when troubleshooting its…