agentmods.dev

shadcn-overview-and-code-ownership

shadcn-overview-and-code-ownership is a skill for Claude Code, Codex from andrewsrigom/agent-skills. It costs 79 tokens per session (803 once invoked), scanned A, original, MIT.

Guidance for deciding whether shadcn/ui fits a project and how to adopt it when the team wants to own the component source code. Unlike a packaged component library, its interface code is copied into and maintained by the application.

In plain words
What is it for?
Use it when evaluating or introducing shadcn/ui, choosing it over a packaged library, or deciding how to organize its components, registries, themes, composition, and forms.
Why use it?
It helps teams choose the right ownership model and avoid confusion about setup, updates, styling, and which follow-up guidance applies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 7mo ago A scan 79 tokens original MIT

Good fit Use it when evaluating or introducing shadcn/ui, choosing it over a packaged library, or deciding how to organize its components, registries, themes, composition, and forms.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership
View source ↗ andrewsrigom/agent-skills andrewsrigom.github.io
Install

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.

Any agent
npx skills add andrewsrigom/agent-skills --skill shadcn-overview-and-code-ownership
Clone the repo
git clone --depth 1 https://github.com/andrewsrigom/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for shadcn-overview-and-code-ownership

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership/github.svg)](https://agentmods.dev/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership)
Your own site
<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership/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.

agentmods 80×15 button for shadcn-overview-and-code-ownership

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/shadcn-overview-and-code-ownership.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.00803
Opus 5.5 $0.00032 $0.00321
Sonnet 5.5 $0.00016 $0.00161
Haiku 4.5 $0.00008 $0.00080

Measured 2mo ago against content hash d30c5d42f611, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shadcn-overview-and-code-ownership 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 2mo 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.

shadcn/shadcn-overview-and-code-ownership/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shadcn Overview And Code Ownership

Use this skill when the task is mainly about whether and how to adopt shadcn in a codebase.

Scope

  • deciding when shadcn is a good fit
  • the code-ownership model behind shadcn
  • default adoption strategy for app teams
  • routing to registry, theming, composition, and forms follow-up skills

Routing cues

  • choose shadcn, adopt shadcn in an app, understand how shadcn differs from packaged component libraries, or decide the overall approach -> use this skill
  • components.json, CLI init, shadcn add, registries, or update workflows -> use shadcn-cli-registry-and-components-json
  • theme tokens, CSS variables, OKLCH colors, dark mode, or design-system defaults -> use shadcn-theming-tokens-and-dark-mode
  • asChild, trigger composition, dialog and dropdown interactions, local component ownership, or wrapper boundaries -> use shadcn-composition-and-trigger-patterns
  • form fields, react-hook-form, validation, or form UI ownership -> use shadcn-forms-and-field-primitives

Default path

  1. Use shadcn when the team wants ownable UI source code instead of a sealed package abstraction.
  2. Start with the official CLI and add only the components the app actually needs.
  3. Treat generated component files as application code you are expected to edit.
  4. Keep local customization close to the component instead of wrapping everything immediately.
  5. Build a thin app-specific UI layer only after repeated patterns are clear.

When to deviate

  • Pick a packaged library instead when the team does not want to own component code.
  • Skip shadcn if the project already has a stable in-house design system with different primitives and conventions.
  • Introduce shared wrappers only after the repetition is real and the ownership boundary is obvious.

Guardrails

  • Treat shadcn components as copied source, not as a magical dependency you should never touch.
  • Keep the app's design tokens and visual defaults coherent before mass-adding components.
  • Prefer a small local surface over a broad imported catalog.
  • Route to sibling skills once the job becomes mostly about theming, registries, composition, or forms.

Read the full file on GitHub · 75 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 75 lines · 79 tokens per session scan A d30c5d42f611

Subscribe to this mod's changes

shadcn-overview-and-code-ownership is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 79 tokens to every session and 803 once invoked, about $0.0003 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 2026-08-31.

Design and UXFrontend
Related

shadcn-overview-and-code-ownership compared with skills from other repositories

shadcn-overview-and-code-ownership next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shadcn-overview-and-code-ownershipandrewsrigom/agent-skillsSkill27mo agoMITA79Claude Code, Codex
webgl-holographic-foilnexu-io/open-designSkill106ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10k2d agoApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code