techtank-site: Skill for Claude Code

.agents/skills/components/SKILL.md

components is a skill for Claude Code, Codex from techtankto/techtank-site. It costs 51 tokens per session (1,448 once invoked), scanned A, original, MIT.

A set of house rules for creating and styling React interface components, including components built with shadcn and Radix. It describes the expected file structure, styling approach, and project organization.

In plain words
What is it for?
Use it when adding, refactoring, or reviewing React components, especially when choosing reusable interface primitives, variants, and layout structure.
Why use it?
It keeps new or changed components consistent with the project's existing code and design patterns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is techtankto/techtank-site's own configuration. It tells Claude Code and Codex how to work on techtank-site 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 techtank-site configures →

Reuse

Borrowing it

Nothing to install: this file belongs to techtankto/techtank-site. 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/techtankto/techtank-site/main/.agents/skills/components/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/techtankto/techtank-site

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 components

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

agentmods 80×15 button for components

Your own site · 80×15
<a href="https://agentmods.dev/skills/techtankto/techtank-site/components"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/components.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 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 $0.00051 $0.01448
Opus 5.5 $0.00020 $0.00579
Sonnet 5.5 $0.00010 $0.00290
Haiku 4.5 $0.00005 $0.00145

Measured 1mo ago against content hash a79eb0f8daa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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/components/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Components

How components are added, shaped, styled, and organized. This skill owns authoring and styling rules; what components exist and what they look like is the design contract's concern, not this skill's.

The flow: shadcn first

  1. Check shadcn before writing anything. Primitives use shadcn, which uses Radix primitives underneath. Adding a new component starts with a check of the shadcn library: if it exists there, import it with the CLI (pnpm dlx shadcn@latest add <name>), then reformat it to the house shape below and re-theme it with the project's design tokens.
  2. Custom components use the identical shape. If shadcn doesn't have it (or the design calls for something bespoke), author it from scratch in exactly the same format; the only difference is there's nothing to import.

The file shape

  1. Every component follows this example skeleton:

    import { forwardRef, type HTMLAttributes } from 'react'
    import { cn, cva, VariantProps } from '@/utils/theme'
    
    const styles = {
      root: cva('…', { variants: { … }, defaultVariants: { … } })
    }
    
    type ExampleRef = HTMLDivElement
    type ExampleProps = HTMLAttributes<ExampleRef> & VariantProps<typeof styles.root>
    
    const Example = forwardRef<ExampleRef, ExampleProps>((props, ref) => {
      // props
      const { className, ...rest } = props
    
      // hooks
    
      // render vars
    
      // jsx
      return <div ref={ref} className={cn(styles.root({ className }))} {...rest}></div>
    })
    Example.displayName = 'Example'
    
    export { Example }
    export type { ExampleProps, ExampleRef }
    

    Order within the file: CVA styles/constants on top → types (XxxRef, XxxProps) → component. Order within the function body, each under its comment: props destructure → hooks → render vars → jsx (composed with cn()).

  2. Named exports only: the component plus its Props and Ref types; displayName set on forwardRef components. No default exports.

Read the full file on GitHub · 94 lines

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 · +7 lines a79eb0f8daa9
  2. 2mo ago First seen · 87 lines · 51 tokens per session scan A 23b05e7242c0

Subscribe to this mod's changes

components is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,448 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 2026-08-31.

Related

components compared with skills from other repositories

components next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
componentstechtankto/techtank-siteSkill53d agoMITA51Claude Code, Codex
chakra-ui-builderchakra-ui/chakra-uiSkill41kyesterdayMITA214Claude Code, Codex
ui-checkstyleopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A122Claude Code
tamagui-v6-configtamagui/tamaguiSkill14ktodayMITA0Claude Code, Codex
tamagui-theme-generatortamagui/tamaguiSkill14ktodayMITA48Claude Code, Codex
frontend-ui-dark-tsmicrosoft/skillsSkill3.2kyesterdayMITA48Claude Code
building-landing-homelobehub/lobe-iconsSkill2.7k3d agoMITA121Claude Code, Codex