What is component-review?

A review checklist for React and TypeScript components. React is a library for building user interfaces, while TypeScript adds type checking to JavaScript; the checklist also covers design-system rules and accessibility.

Use it to review a component against its surrounding code, design-system tokens, variant and property contracts, accessibility expectations, and TypeScript practices. It produces findings with small suggested fixes.

It finds concrete problems before a component is merged, including incorrect visual tokens, mismatched properties, keyboard or contrast issues, and TypeScript convention violations.

How personaxis/persona.md configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to personaxis/persona.md. 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/personaxis/persona.md/main/.claude/skills/component-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/personaxis/persona.md

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/personaxis/persona.md/component-review/github.svg)](https://agentmods.dev/skills/personaxis/persona.md/component-review)

Your own site

<a href="https://agentmods.dev/skills/personaxis/persona.md/component-review"><img src="https://agentmods.dev/badge/skills/personaxis/persona.md/component-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/personaxis/persona.md/component-review"><img src="https://agentmods.dev/badge/skills/personaxis/persona.md/component-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 421 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	$0.00035	$0.00421
Opus 5.5	$0.00014	$0.00168
Sonnet 5.5	$0.00007	$0.00084
Haiku 4.5	$0.00003	$0.00042

Measured 1mo ago against content hash 2755e46a71f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

component-review 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.

.claude/skills/component-review/SKILL.md · 44 lines

What it actually says

Component Review

Use this skill when asked to review a React/TypeScript component before it merges, or to audit an existing component for design-system and accessibility compliance.

Steps

Read the component file(s) end to end before flagging anything - do not review based on a diff alone if the surrounding file changes the context (e.g. a prop added elsewhere in the file).
Check design-system tokens. Colors must resolve to semantic tokens (no raw hex, no off-list palette utilities). Spacing, radius, shadow, and border values must use the project's documented tokens. Typography must use the sanctioned type scale.
Check variant and prop contracts. The component should use an existing variant before introducing a new one. Props must match the documented component contract (names, types, defaults). Flag ad-hoc className overrides that fight the base component's styles.
Check accessibility. All interactive elements reachable via keyboard, visible focus states matching the documented focus-ring spec, form controls with associated labels, WCAG AA contrast, decorative vs. meaningful icons handled correctly.
Check TypeScript conventions. Props typed with interface (not any), no unchecked as casts without a documented reason, exported types match what consumers need.
For the full checklist with every sub-item, load references/component-review-checklist.md - it is not duplicated here to avoid drift between this skill and the reference.

Output format

Each finding as [rule violated] -> [location] -> [minimal fix]. No preamble, no summary unless requested. If the component passes every check, say so in one line.

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.

.personaxis-generated 119 B

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.

1mo ago First seen · 44 lines · 35 tokens per session scan A 2755e46a71f1

Subscribe to this mod's changes

component-review is a skill published in the GitHub repository personaxis/persona.md (8 stars, last pushed 28d ago), licensed MIT. It adds 35 tokens to every session and 421 once invoked, about $0.0001 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 2026-10-02.

Design and UX Frontend React ai-agents ai-personas

component-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
component-reviewpersonaxis/persona.md	Skill	8	28d ago	MIT	A	35	Claude Code
3d-web-experienceratnesh-maurya/cursor-claude-personas	Skill	12	7mo ago	MIT	A	53	Claude Code
chakra-ui-builderchakra-ui/chakra-ui	Skill	41k	yesterday	MIT	A	214	Claude Code, Codex
tamagui-v6-configtamagui/tamagui	Skill	14k	today	MIT	A	0	Claude Code, Codex
tamagui-theme-generatortamagui/tamagui	Skill	14k	today	MIT	A	48	Claude Code, Codex
frontend-ui-dark-tsmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	48	Claude Code
cobejsMengTo/Skills	Skill	7.3k	yesterday	MIT	A	31	Claude Code, Codex

persona.md: Skill for Claude Code