interface-review

interface-review is a skill for Claude Code, Codex from PrabhdeepSingh/claude-plugins. It costs 96 tokens per session (1,447 once invoked), scanned A, original, MIT.

A coordinated review of a complete interface, such as a screen, user flow, or feature. It combines checks for accessibility, layout, wording, typography, color, visual finish, and motion into one prioritized result.

In plain words
What is it for?
Auditing an interface in quick or full mode, including important user paths and states such as loading, errors, empty screens, and narrow windows.
Why use it?
It brings separate design checks together so problems are ranked across the whole experience rather than reported as disconnected reviews.

Skill for Claude CodeCodex

Part of the sonu plugin — 26 skills, 3 commands shipped together

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.

agentmods
npx agentmods add skills/prabhdeepsingh/claude-plugins/interface-review
Any agent
npx skills add PrabhdeepSingh/claude-plugins --skill interface-review
Clone the repo
git clone --depth 1 https://github.com/PrabhdeepSingh/claude-plugins

Made for: Claude Code, Codex.

Or install sonu, the plugin that ships this one along with the rest of its 26 skills, 3 commands.

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 interface-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/interface-review.svg)](https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/interface-review)
Your own site
<a href="https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/interface-review"><img src="https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/interface-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00096 $0.01447
Opus 5 $0.00048 $0.00724
Sonnet 5 $0.00019 $0.00289
Haiku 4.5 $0.00010 $0.00145

Measured 3d ago against content hash 0fa5d3bc969f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interface-review scanned grade A with 1 finding 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 3d 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.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

Identify the framework, styling system, design tokens, and available preview or test commands first — findings must follow the project's own conventions. Availability of the domain skills is then discovered by attempting

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

sonu/skills/interface-review/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review the interface as one system

A strong interface is not six independent audits stapled together. Review the whole experience, let each domain skill own its rules, then consolidate the evidence into one prioritized verdict. This skill owns orchestration only: accessibility rules belong to [[accessibility]], structure to [[layout]], copy to [[ux-writing]], type to [[typography]], color to [[colors]], polish and motion to [[ui-polish]]. Never duplicate or override their rules here.

1. Resolve Scope and Mode

Apply this to $ARGUMENTS — the text typed after the invocation, carrying an optional mode (quick or full) and an optional scope. If that token appears literally or is empty, infer the scope from the request and workspace, and use full. State the resolved scope in the output.

Mode Coverage Finding cap
quick Primary user path and highest-traffic states; report only HIGH and MEDIUM 5
full Entire requested scope across all six domains, including empty, loading, error, and narrow-width states 15

If the scope is too large to inspect credibly, narrow it to the highest-traffic complete flow and state the boundary — never imply uninspected surfaces were reviewed. A review is read-only: implement findings only when the user also asks for that, and re-run the relevant verification afterward.

2. Load the Domain Skills

Identify the framework, styling system, design tokens, and available preview or test commands first — findings must follow the project's own conventions. Availability of the domain skills is then discovered by attempting the load — there is no way to enumerate installed skills without trying. Invoke each in this order, so foundational failures are not hidden by polish: Skill(sonu:accessibility), Skill(sonu:layout), Skill(sonu:ux-writing), Skill(sonu:typography), Skill(sonu:colors), Skill(sonu:ui-polish). A load that fails marks that domain Not reviewed — name the missing skill, continue with the rest, and never recreate its rules from memory, substitute a neighbor, or claim holistic coverage.

Read the full file on GitHub · 62 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. 3d ago First seen · 62 lines · 96 tokens per session scan A 0fa5d3bc969f

Subscribe to this mod's changes

interface-review is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 1,447 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

design-sprint

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…

wondelai/skills · 137 tokens

hooked-ux

Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when the user mentions "users arent coming back", "habit formation", "engagement loops", "habit zone", or "the manipulation matrix". Also trigger when designing notification or re-engagement strategies, building…

wondelai/skills · 109 tokens

create-website

Guided journey from a blank page to a live, high-converting website, built message-first, then design, then conversion. Orchestrates ten skills phase by phase - one-page-marketing, storybrand-messaging, made-to-stick, top-design, web-typography, refactoring-ui, ux-heuristics, cro-methodology, scorecard-marketing…

wondelai/skills · 228 tokens

grow-app

Guided journey from an app people sign up for and then quietly abandon to a sealed retention engine with a habit loop, an activated first run, and one metric the whole team trusts. Orchestrates eight skills phase by phase - hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics…

wondelai/skills · 198 tokens

improve-app

Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick…

wondelai/skills · 236 tokens

improve-code-quality

Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…

wondelai/skills · 227 tokens