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 Kemdirimakujuobi/skills --skill building-componentsgit clone --depth 1 https://github.com/Kemdirimakujuobi/skillsWrote 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/kemdirimakujuobi/skills/building-components)<a href="https://agentmods.dev/skills/kemdirimakujuobi/skills/building-components"><img src="https://agentmods.dev/badge/skills/kemdirimakujuobi/skills/building-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/kemdirimakujuobi/skills/building-components"><img src="https://agentmods.dev/badge/skills/kemdirimakujuobi/skills/building-components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00177 | $0.03183 |
| Opus 5.5 | $0.00071 | $0.01273 |
| Sonnet 5.5 | $0.00035 | $0.00637 |
| Haiku 4.5 | $0.00018 | $0.00318 |
Grade A, and why
building-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 13d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building components
Every component is the same three things stacked, in this order. Get the order wrong and you get an inaccessible or off-brand component that looks done but isn't.
- A headless primitive library is the base. Behaviour, ARIA, focus management, keyboard support, all bundled, all from the full primitive (Radix, React Aria, Base UI, whichever your repo uses). You never hand-roll accessibility.
- Your semantic tokens are the only paint. Headless primitives ship unstyled on purpose. You style them with semantic CSS variables and nothing else: no hex, no palette utilities, no eyeballed pixel values. The values come from the design file, read exactly.
- The doc contract is the finish line. A component isn't done when it renders. It's done when it has the agent- and human-first docs.
This skill is the procedure. The rules live in docs/standards/STANDARDS.md (CODE-, COMP-,
DOCS-); this skill tells you the order to apply them in and why each step matters. Radix is the
worked example throughout; the same steps apply to any headless library.
Configure for your repo
The skill expects to find, and falls back as noted:
- Primitive library: read
package.jsonfor@radix-ui/*,react-aria-components,@base-ui-components/*or similar. If none, propose one and log it as a decision before building. - Exemplar: your repo's best-built component (its source, stories and doc page).
AGENTS.mdshould name it; if not, pick the one with the most complete docs and ask the user to confirm. Copy its shape: variant helper, class-merge utility, file layout. - Token output: where generated semantic tokens live (see
design-tokens). - Staging vs library: if the repo has a lint-ignored staging folder for work in progress and
a lint-enforced library folder,
AGENTS.mdsays where. If not, build straight in the library. - Component inventory: a doc listing which components are greenlit. If none, the user's request is the scope.
- Docs surface: Storybook (MDX + stories) by default; plus any machine-readable manifest
(
registry.json,llms.txt) the repo publishes. - Scripts:
npm run lint, the docs build (build-storybook), the docs a11y test runner, and any barrel/index generator. Read names frompackage.json; if a script is missing, say so rather than skipping the check.
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.
- 13d ago First seen · 216 lines · 177 tokens per session scan A caa3dd82ebf9
building-components is a skill published in the GitHub repository Kemdirimakujuobi/skills (9 stars, last pushed 13d ago), licensed MIT. It adds 177 tokens to every session and 3,183 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…
memoire-design-tooling
Set up and operate Mémoire's CLI, MCP server, agent kits, design preflight, UX audits, craft checks, tokens, and registry evidence. Use when a repository explicitly needs Mémoire tooling; use portable design skills when Mémoire is unavailable.
better-ui
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better"…
token-architecture
Map design values to an existing token system and plan safe token changes across themes and consumers. Use for token drift, Figma variable alignment, or cross-surface theming.
design-to-code-handoff
Carry Figma or Paper design evidence into an existing web codebase, design system, Storybook, and browser verification. Use when an agent must implement a supplied design without losing source context or inventing components.
better-colors
OKLCH color space for web projects. Convert hex/rgb/hsl to oklch, generate palettes, check contrast, handle gamut boundaries, and theme with Tailwind v4. Triggers on oklch, color conversion, palette generation, contrast ratio, gamut, display p3, design tokens, hue drift, chroma, dark mode colors.