agentmods.dev

palot: Skill for Codex

.agents/skills/shadcn/SKILL.md

shadcn is a skill for Codex from ItsWendell/palot. It costs 60 tokens per session (704 once invoked), scanned A, original, MIT.

A repository-specific skill for managing shadcn/ui components, which are reusable interface components generated and maintained with the shadcn command-line tool. It covers adding, updating, composing, and debugging those components in Palot.

In plain words
What is it for?
Use it when changing shadcn components, component registries, presets, or related configuration, or when running the shadcn command in the desktop app.
Why use it?
It helps avoid mismatches between the pinned command-line tool, local component code, configuration, aliases, and styling setup. It also directs developers to inspect existing components before replacing or adding them.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions OpenCode.

This is ItsWendell/palot's own configuration. It tells Codex how to work on palot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything palot configures →

not rated 194repo +1 changed 1mo ago A scan 60 tokens original MIT
View source ↗ ItsWendell/palot
Reuse

Borrowing it

Nothing to install: this file belongs to ItsWendell/palot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ItsWendell/palot/main/.agents/skills/shadcn/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ItsWendell/palot

Made for: 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/itswendell/palot/shadcn/github.svg)](https://agentmods.dev/skills/itswendell/palot/shadcn)
Your own site
<a href="https://agentmods.dev/skills/itswendell/palot/shadcn"><img src="https://agentmods.dev/badge/skills/itswendell/palot/shadcn/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/itswendell/palot/shadcn"><img src="https://agentmods.dev/badge/skills/itswendell/palot/shadcn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 704 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 $0.00060 $0.00704
Opus 5.5 $0.00024 $0.00282
Sonnet 5.5 $0.00012 $0.00141
Haiku 4.5 $0.00006 $0.00070

Measured 1mo ago against content hash 555f3b240075, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shadcn 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 1mo 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.

.agents/skills/shadcn/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shadcn/ui in Palot

Palot pins the shadcn CLI in apps/desktop. Run it from that workspace through Vite+:

vp exec -- shadcn info --json
vp exec -- shadcn docs <component>

Do not use npx, pnpm dlx, bunx, or an @latest CLI. Preserve the repository pin and the aliases, Tailwind file, primitive base, icon library, and registries reported by info.

Choose the work

  • Existing-source fixes: inspect the component and relevant callers first. Use the local implementation as the contract; CLI discovery and external docs are unnecessary when that evidence answers the question.
  • Adding components or changing registry/configuration: read repository-root ../../../apps/desktop/components.json and run vp exec -- shadcn info --json from apps/desktop. Prefer existing local primitives and variants; use search or view when looking for a missing component.
  • Unclear APIs or upstream behavior: use vp exec -- shadcn docs <component> and fetch the relevant returned documentation. Reconcile it with the local source before applying it to customized components.
  • Upstream component updates: follow the preview workflow below.

Inspect changed imports and CSS where applicable, then follow the formatting and validation workflow in the development guide. Shadcn CLI edits bypass OpenCode's native formatter hook, so format those files explicitly while respecting the repository's exclusions.

Updating components

Use the CLI rather than fetching upstream source manually:

  1. Run vp exec -- shadcn add <component> --dry-run to list affected files.
  2. Run vp exec -- shadcn add <component> --diff <file> for each customized file.
  3. Apply upstream changes while preserving local behavior and imports.
  4. Use --overwrite only when the user explicitly authorizes replacing local changes.

Project rules

  • Use semantic theme tokens rather than raw colors or manual dark-mode overrides.
  • Use gap-*, size-*, truncate, and cn() rather than equivalent verbose utilities.
  • Compose forms with FieldGroup and Field; put collection items inside their matching group.
  • Dialog-like surfaces require an accessible title.
  • Prefer shared components such as Alert, Empty, Separator, Skeleton, and Badge over hand-built equivalents.
  • Keep layout decisions in call sites and reusable visual behavior in component variants.

Read the full file on GitHub · 58 lines

Files

What ships with it

16 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.

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. 1mo ago Changed 555f3b240075
  2. 1mo ago First seen · 58 lines · 60 tokens per session scan A 9acfabd9f5f6

Subscribe to this mod's changes

shadcn is a skill published in the GitHub repository ItsWendell/palot (194 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 704 once invoked, about $0.0002 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 2026-09-13.

Design and UXFrontendagentic-codingai-agentai-coding-assistantanthropicclaudecodex
Related

shadcn compared with skills from other repositories

shadcn next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shadcnItsWendell/palotSkill1942d agoMITA60Codex
mobile-ios-designHigorAlves/orcSkill7todayMITA16Claude Code
design-systemtmj-90/gafferSkill22d agoApache-2.0A122Claude Code, Codex
brandtmj-90/gafferSkill22d agoApache-2.0A102Claude Code, Codex
tailwind-design-systemHigorAlves/orcSkill7todayMITA23Claude Code
orc-mobile-ios-designHigorAlves/orcSkill7todayMITA17Codex
frontend-a11ytmj-90/gafferSkill22d agoApache-2.0A83Claude Code, Codex