polish-pass

polish-pass is a skill for Claude Code, Codex from OneWave-AI/open-agent-stack. It costs 51 tokens per session (571 once invoked), scanned A, original, MIT.

A final review process for AI-built web apps that checks their visual design and wording, then makes targeted improvements to layout, motion, and copy.

In plain words
What is it for?
Use it after building an app to audit its interface, vary its page structure, improve small pieces of text, and make the result feel more deliberately designed.
Why use it?
It helps remove repetitive template-like design and generic AI wording before an app is shown to others.

Skill for Claude CodeCodex

Part of the vibe-stack plugin — 14 skills, 1 command, 1 agent 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/onewave-ai/open-agent-stack/polish-pass
Any agent
npx skills add OneWave-AI/open-agent-stack --skill polish-pass
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack

Made for: Claude Code, Codex.

Or install vibe-stack, the plugin that ships this one along with the rest of its 14 skills, 1 command, 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 polish-pass

README.md
[![agentmods](https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/polish-pass.svg)](https://agentmods.dev/skills/onewave-ai/open-agent-stack/polish-pass)
Your own site
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/polish-pass"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/polish-pass.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00051 $0.00571
Opus 5 $0.00026 $0.00285
Sonnet 5 $0.00010 $0.00114
Haiku 4.5 $0.00005 $0.00057

Measured 4d ago against content hash cb8a561eb630, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

polish-pass 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 4d 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/vibe-stack/skills/polish-pass/SKILL.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Polish Pass

Everyone can tell. The centered-hero-with-gradient-text, the three-feature-cards-with-icons, the "Unlock the power of" copy -- AI-built apps share a look, and losing it is the difference between a demo and a product. This pass hunts the tells and replaces them with decisions.

Workflow

  1. The tells audit. Sweep design and copy for the fingerprints: symmetric three-card grids, gradient text on dark hero, purple anywhere, emoji as icons, identical border-radius-and-shadow on every element, "Unlock/Supercharge/Seamlessly" copy, feature names that describe categories not benefits, every section the same width and rhythm. List each with location.
  2. Break the symmetry. Editorial moves: vary section rhythm (one full-bleed, one narrow, one asymmetric), let one element be genuinely large, use whitespace as a feature, align to a real grid but break it once deliberately. The page should read like it was art-directed, not generated.
  3. Rewrite the words. Copy passes the read-aloud test: specific over sweeping ("invoices chase themselves" not "streamline your workflow"), numbers where they exist, the user's vocabulary, zero filler adjectives. Microcopy too -- buttons, empty states, and errors are where products feel human or robotic.
  4. Motion with intent. Replace scattered hover effects with a small motion system: one entrance treatment, one emphasis move, consistent durations and easings. Motion that communicates hierarchy, not motion because an animation library was installed. If the app has more than three or four distinct durations, stop and run motion-system -- this is a systemic fix, not a per-element one. micro-interactions covers the hover/press/focus set, and motion-perf covers it stuttering on a phone.
  5. Detail sweep. Favicon and OG image real, focus states designed (not default blue), empty/loading/error states written, dark surfaces layered by elevation not one flat color, and typography checked at actual phone size.

Read the full file on GitHub · 24 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. 4d ago First seen · 24 lines · 51 tokens per session scan A cb8a561eb630

Subscribe to this mod's changes

polish-pass is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 24d ago), licensed MIT. It adds 51 tokens to every session and 571 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.

Related

Other skills, from other repositories

sketch

Throwaway HTML mockups: 2-3 design variants to compare.

NousResearch/hermes-agent · 18 tokens

impeccable

Frontend design guidance, upstream-maintained (impeccable).

NousResearch/hermes-agent · 18 tokens

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

ThinkInAIXYZ/deepchat · 64 tokens

design-tokens-transformer

하나의 브랜드 토큰을 3계층(DTCG SSOT ↔ 원시 CSS 변수 ↔ semantic/shadcn 롤)으로 양방향 변환합니다. L1 DTCG(W3C $value/$type/$description)를 진실 원천으로 삼아 L2 CSS custom properties와 L3 Tailwind v4 @theme + .dark 전환 체계를 파생하고, 역방향(코드→DTCG)과 라운드트립 무결성 검사도 지원합니다. handoff 번들의 3계층 인코딩(02-tokens.json / colorsandtype.css / globals.css)을 자동 변환하는 파이프라인입니다. 다음과…

modu-ai/moai-cowork · 255 tokens

design-brand-system

웹 프로젝트의 브랜드 정합 시각 디자인 시스템 전문가. 히어로 우선 레이아웃 체이닝, WCAG 2.1 AA 접근성, Lighthouse 80점 이상, 브랜드 정체성 파일에서 디자인 토큰 추출을 보장합니다. 색상 팔레트, 타이포그래피, 여백, 컴포넌트 사양을 다룹니다. Use for brand-aligned visual design systems: color palettes, typography, spacing systems, hero-first layout, component specs, design tokens, visual identity, and WCAG…

modu-ai/moai-cowork · 130 tokens

design-landing-motion

기억에 남는 다이나믹 랜딩 페이지를 만듭니다. 브리프에서 컨셉 스파인을 뽑고, 시그니처 효과를 하나만 골라 끝까지 완성하며, 화면에 들어갈 비주얼은 Higgsfield로 생성해 브랜드 팔레트에 잠급니다. 스크롤 스크럽·시차 레이어·WebGL 디스플레이스먼트·파티클·마스크 리빌·수평 레일·키네틱 타이포 등을 다루고, React/Next(R3F·Framer Motion·GSAP)와 정적 사이트(바닐라 three.js·GSAP) 양쪽으로 냅니다. 다음과 같은 요청 시 사용하세요: "랜딩 페이지 만들어 줘", "히어로 인상적으로" "스크롤에 반응하는 사이트", "스크롤하면…

modu-ai/moai-cowork · 319 tokens