review

review is a command for Claude Code from opkod-france/opkod-claude-code-plugins. It costs 12 tokens per session (207 once invoked), scanned A, original, MIT.

A read-only UI review command that checks a component against Refactoring UI design guidelines, including layout, text, color, and common interface patterns.

In plain words
What is it for?
Use it to review a UI component or several related files and receive a structured list of strengths, problems, severity levels, fixes, and quick improvements.
Why use it?
It finds visual and usability problems without changing your files, and gives you a consistent way to decide which improvements matter most.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents; positional $N argument.

Part of the ui-polish plugin — 1 skill, 2 commands, 1 agent shipped together

Good fit Use it to review a UI component or several related files and receive a structured list of strengths, problems, severity levels, fixes, and quick improvements.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/opkod-france/opkod-claude-code-plugins/review
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.

Clone the repo
git clone --depth 1 https://github.com/opkod-france/opkod-claude-code-plugins

Made for: Claude Code.

Or install ui-polish, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 agent.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/opkod-france/opkod-claude-code-plugins/review/github.svg)](https://agentmods.dev/commands/opkod-france/opkod-claude-code-plugins/review)
Your own site
<a href="https://agentmods.dev/commands/opkod-france/opkod-claude-code-plugins/review"><img src="https://agentmods.dev/badge/commands/opkod-france/opkod-claude-code-plugins/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/opkod-france/opkod-claude-code-plugins/review"><img src="https://agentmods.dev/badge/commands/opkod-france/opkod-claude-code-plugins/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 207 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 $0.00012 $0.00207
Opus 5 $0.00006 $0.00103
Sonnet 5 $0.00002 $0.00041
Haiku 4.5 $0.00001 $0.00021

Measured 9d ago against content hash 76c4da2181c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

plugins/ui-polish/commands/review.md · 26 lines

What it actually says

Review the UI component at @$1 using the refactoring-ui skill (load it for the full criteria set: hierarchy, spacing, typography, color, shadcn patterns, anti-patterns).

For larger reviews spanning multiple files, delegate to the ui-reviewer sub-agent for context isolation.

Output

Structured review:

  1. Summary — one-sentence assessment.
  2. Strengths — what the component does well (be specific).
  3. Issues Found — for each:
    • Location (line number or element)
    • Problem
    • Severity (Critical / Important / Minor)
    • Suggested fix with a small code example
  4. Quick Wins — 2–3 highest-impact changes.

Read-only — do NOT modify files.

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. 9d ago First seen · 26 lines · 12 tokens per session scan A 76c4da2181c2

Subscribe to this mod's changes

review is a command published in the GitHub repository opkod-france/opkod-claude-code-plugins (9 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 207 once invoked, about $0.0001 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.