superui-review

superui-review is a skill for Claude Code, Codex from HappyDoggyAI/superui. It costs 67 tokens per session (1,287 once invoked), scanned A, original, MIT.

A review workflow for checking frontend plans, designs, code, tests, and visual results. It uses several independent reviews before combining their findings into a final decision.

In plain words
What is it for?
Use it for plan reviews, code reviews, quality checks, visual testing, and improvement plans for frontend projects.
Why use it?
It helps find missing requirements, broken interactions, accessibility problems, responsive issues, and differences from the design before release.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents; $skill-name invocation.

Part of the superui plugin — 6 skills shipped together

Good fit Use it for plan reviews, code reviews, quality checks, visual testing, and improvement plans for frontend projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happydoggyai/superui/superui-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.

Any agent
npx skills add HappyDoggyAI/superui --skill superui-review
Clone the repo
git clone --depth 1 https://github.com/HappyDoggyAI/superui

Made for: Claude Code, Codex.

Or install superui, the plugin that ships this one along with the rest of its 6 skills.

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 superui-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/happydoggyai/superui/superui-review/github.svg)](https://agentmods.dev/skills/happydoggyai/superui/superui-review)
Your own site
<a href="https://agentmods.dev/skills/happydoggyai/superui/superui-review"><img src="https://agentmods.dev/badge/skills/happydoggyai/superui/superui-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 superui-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/happydoggyai/superui/superui-review"><img src="https://agentmods.dev/badge/skills/happydoggyai/superui/superui-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,287 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 $0.00067 $0.01287
Opus 5 $0.00034 $0.00643
Sonnet 5 $0.00013 $0.00257
Haiku 4.5 $0.00007 $0.00129

Measured 10d ago against content hash afce5de3e3b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

superui-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 10d 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.

skills/superui-review/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross Review And Convergence

Run Plan Gate and Code Gate reviews through three independent perspectives and one Chairman. The goal is not to nitpick; it is to make frontend artifacts resilient, evidence-backed, and shippable.

Core Rules

  • Read skills/superui-shared/rubric-locked.md at review start and keep the rubric unchanged for the whole review.
  • Always load rubric-locked.md; load other shared files only when the gate or dispute requires them.
  • Run three isolated reviewers when subagents are available. If not, the main agent must perform the three roles separately and avoid cross-contamination.
  • The Chairman aggregates, asks questions, and decides. The Chairman must not introduce new review findings.
  • Stop after at most three question rounds. Non-core disagreements get a default Chairman decision; core conflicts go to review-conflicts.json for human decision.
  • Write all review reports, disagreements, repair notes, and decisions under <ARTIFACT_ROOT>/review/.
  • Read skills/superui-shared/TASK_MANAGEMENT.md; update todo.md, append gate evidence to progress.md, and update pipeline-status.md.

Gate Triggers

Gate Trigger Artifacts to review
Plan Gate proposal.md or design-proposal.md exists plan artifact + DESIGN.md
Code Gate implementation and tests are ready code + tests + DESIGN.md + design-adjustments.md

Both gates use the same three-role plus Chairman process.

Load Standards

Condition Load
Always rubric-locked.md
Plan Gate ENGINEERING_GATES.md, DESIGN_HANDOFF_CHECKLIST.md
Code Gate ENGINEERING_GATES.md, RESPONSIVE_RULES.md
Style, industry, trust, or anti-pattern disputes DESIGN_INTELLIGENCE.md
Delivery completeness, states, assets, or error pages DESIGN_HANDOFF_CHECKLIST.md

Record briefly when an optional shared file is not loaded.

Reviewer Roles

Critic

Focus on user requirements and product behavior.

Read the full file on GitHub · 148 lines

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.

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. 10d ago First seen · 148 lines · 67 tokens per session scan A afce5de3e3b2

Subscribe to this mod's changes

superui-review is a skill published in the GitHub repository HappyDoggyAI/superui (2 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,287 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.