What is pi-ui-review?

A command that asks Gemini, an AI assistant, to inspect frontend code for user-interface and user-experience problems.

Review a frontend file or components directory for accessibility, responsive design, and component-structure concerns; a supplied screenshot can instead be analyzed by Claude.

It helps identify accessibility issues, poor behavior on different screen sizes, and problems in how interface components are organized.

pi-ui-review — Command for Claude Code by tznthou

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/tznthou/claude-prism

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/commands/tznthou/claude-prism/pi-ui-review/github.svg)](https://agentmods.dev/commands/tznthou/claude-prism/pi-ui-review)

Your own site

<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-ui-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-ui-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/commands/tznthou/claude-prism/pi-ui-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-ui-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,091 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	$0.00014	$0.03091
Opus 5	$0.00007	$0.01545
Sonnet 5	$0.00003	$0.00618
Haiku 4.5	$0.00001	$0.00309

Measured 12d ago against content hash e5c2649be62c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pi-ui-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 12d 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.

commands/pi-ui-review.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Review via Gemini

Use Gemini (via agy, the Antigravity CLI) to perform UI/UX review on frontend code. Gemini brings Google Design ecosystem knowledge and frontend best practices.

Limitation: the agy-based headless wrapper does not pass image input. If the user provides screenshots, use Claude's own multimodal capability.

Execution

Bash invocation rules (v0.12.3+): Call call-codex.sh / call-gemini.sh in foreground synchronous mode with timeout: 600000 (Bash tool's 10-minute ceiling). Do not use &, do not set run_in_background: true, do not use nohup — Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the process (output file stays 0 bytes). Use run_in_background: true + BashOutput polling only as an exception when the call is genuinely expected to exceed 10 minutes.

1. Determine review scope

Based on $ARGUMENTS:

File path: review the specified frontend file
Directory path: review an entire components directory (list files for user to choose)
--screenshot <path>: screenshot analysis (use Claude multimodal, skip Gemini)
--verbose: also show issues that were filtered out (< 80 confidence) with their scores

1.5 Gather project guidelines

Search for project guideline files to use as compliance context:

for f in CLAUDE.md .claude/CLAUDE.md Agents.md .claude/Agents.md; do
  [ -f "$f" ] && echo "=== $f ===" && cat "$f"
done

If any guideline files are found, include them in the Gemini prompt and confidence scoring.
If none are found, skip the guideline compliance dimension.

1.7 Gather historical PR comments (when reviewing PR-related changes)

If the code being reviewed is part of a PR or recent branch work, search for recurring review patterns:

Get recently changed files: git diff main...HEAD --name-only (or the files being reviewed)
Find recent merged PRs: gh pr list --state merged --limit 10 --json number,title

For each (up to 5), fetch review comments on the same files:

gh api "repos/{owner}/{repo}/pulls/NUMBER/comments" \
  --jq '.[] | select(.path == "TOUCHED_FILE") | {path, body}'

Include found comments as additional context in the Gemini prompt (Step 3), prefixed with: "Historical Review Context (previous review comments on the same files — recurring issues are high-confidence signals):"

Read the full file on GitHub · 260 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.

12d ago First seen · 260 lines · 14 tokens per session scan A e5c2649be62c

Subscribe to this mod's changes

pi-ui-review is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 3,091 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.

Claude Code Code review Design and UX Frontend ai-code-review bash github-actions multi-provider

init-brand-tokens

Generate OKLCH design tokens with WCAG validation, shadcn/ui integration, and Tailwind v4 theming via 8 customization questions.

marcusgoll/Spec-Flow · 0 tokens

critique

Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.

educlopez/ui-craft · 56 tokens

pi-ui-review