What is update-component?

A planned workflow for auditing and updating an existing interface component, its Storybook example, and its specification document. It checks the implementation against shared coding and accessibility conventions before making changes.

Use it when fixing or improving an existing component, filling gaps in its Storybook story, correcting accessibility or style violations, or updating an out-of-date specification.

It helps find mismatches between component code, examples, documentation, and project standards. Planning first makes the proposed changes reviewable before files are edited.

How brianmontanaweb/agentic-design-system configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to brianmontanaweb/agentic-design-system. 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/brianmontanaweb/agentic-design-system/main/.claude/skills/update-component/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/brianmontanaweb/agentic-design-system

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brianmontanaweb/agentic-design-system/update-component.svg)](https://agentmods.dev/skills/brianmontanaweb/agentic-design-system/update-component)

Your own site

<a href="https://agentmods.dev/skills/brianmontanaweb/agentic-design-system/update-component"><img src="https://agentmods.dev/badge/skills/brianmontanaweb/agentic-design-system/update-component.svg" alt="Measured on agentmods" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,330 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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.02330
Opus 5	$0.00034	$0.01165
Sonnet 5	$0.00014	$0.00466
Haiku 4.5	$0.00007	$0.00233

Measured 7d ago against content hash 9096d64d48e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

update-component 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 7d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (evals/scripts/grade-agentstatus.sh, evals/scripts/grade-button.sh, evals/scripts/grade-toolcallcard.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/update-component/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Component

Audit and update an existing component given $ARGUMENTS in the format <ComponentName>.

Gotchas

These defuse the most common mistakes before you encounter them:

Read references/violation-criteria.md once in Step 2 — it stays in context for Steps 4–6; do not re-read it.
The underlying conventions live in .claude/skills/shared/references/ — conventions.md (imports, tokens, layout) and aria-patterns.md (required ARIA per component type) are the single source of truth shared with the add-component skills; violation-criteria.md tells you how to flag deviations from them.
Figma is optional — if the user skips the link, mark "Figma: skipped" in the plan and proceed immediately; never block on it.
color.on.accent is not a hex violation — it is a Chakra semantic token name; do not flag it as a hardcoded color. Do add it to the spec doc's tokens.colors array if it appears in source style props — it is a real token reference that belongs in the tokens completeness inventory.
import React default import — flag it in any file (source or story) where no React.* type annotations (React.ReactElement, React.MouseEvent, React.ReactNode) appear; do not flag it if any such annotations are present. Actively scan before deciding.
SC 1.4.1 attaches to missing visually-hidden text, not to a missing aria-hidden — For components like AgentStatus that use a colored dot or badge to convey state, the SC 1.4.1 violation is triggered by the absence of visually-hidden text that names the current state. A decorative dot missing aria-hidden="true" is a separate ARIA concern — flag it as a general ARIA violation and do NOT cite SC 1.4.1 for it.
Fixing SC 1.4.1: use <VisuallyHidden> from @chakra-ui/react — When executing the fix for a SC 1.4.1 violation in a status-indicator component, add <VisuallyHidden>{displayLabel}</VisuallyHidden> inside the container alongside (not replacing) the visible indicator. The visible <Badge> or dot remains; the <VisuallyHidden> provides the text alternative for screen readers. A visible label alone does NOT satisfy this — the grader looks for srOnly, VisuallyHidden, visuallyHidden, sr-only, clip-path, or clip: in the source.
Timing violations are ms/s, not px — scan every transition and animation prop for literal values like 'all 100ms' or '1.2s ease-in-out'; these are token violations even though they contain no #.
Tokens field completeness requires active scanning — extract every token string from the source style objects and compare against the spec doc's tokens arrays; do not rely on memory or assume the list is complete.
'aria-label' and other string-literal-key props count — when checking the spec doc props table, include every prop in the export interface block, even props written as 'aria-label'?: string.
Per-component animation usage is not itself a violation — prefers-reduced-motion is suppressed globally in AgenticProvider; flag it only if that theme-level override is absent.
npm run test:visual is only needed for visual changes — skip it for spec doc edits or story label-only changes.

Read the full file on GitHub · 197 lines

Files

What ships with it

23 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.

7d ago First seen · 197 lines · 68 tokens per session scan A 9096d64d48e9

Subscribe to this mod's changes

update-component is a skill published in the GitHub repository brianmontanaweb/agentic-design-system (3 stars, last pushed 17d ago), licensed MIT. It adds 68 tokens to every session and 2,330 once invoked, about $0.0003 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 2026-08-31.

Design and UX Frontend accessibility agentic ai-agents chakra-ui component-library design-system

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

productdevbook/shadcn-htmx · 90 tokens

handoff-spec

Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use design-qa-checklist; for reusable library components use component-spec (design-systems).

Owl-Listener/designer-skills · 57 tokens

animation-principles

Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.

Owl-Listener/designer-skills · 59 tokens

readable-measure

Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.

Owl-Listener/designer-skills · 44 tokens

von-restorff-effect

Apply the Von Restorff Effect — the element that differs from its neighbours is the one remembered. Use when a single action must dominate. For overall ordering rather than single-element emphasis, use visual-hierarchy.

Owl-Listener/designer-skills · 49 tokens

color-system

Build a product colour system — tonal scales, semantic roles, and contrast compliance. Use when defining or rebuilding colour from scratch. For dark-mode adaptation use dark-mode-design; for chart palettes use data-visualization; for multi-brand token architecture use theming-system (design-systems).

Owl-Listener/designer-skills · 64 tokens

agentic-design-system: Skill for Claude Code