redesign-codex-ui

A design and implementation guide for changing an existing Codex desktop or web interface around a reference image, persona, theme, or visual style. It treats the existing interface and its working behavior as part of the design task.

In plain words
What is it for?
Use it to redesign Codex screens, translate a character or style into a complete interface theme, inspect a local Codex installation, and apply changes to the real UI.
Why use it?
It helps turn visual inspiration into consistent choices for layout, density, colors, typography, navigation, interaction, accessibility, and terminology. It reduces the risk of making only a decorative mockup that breaks the product’s behavior.

Skill for Claude CodeCodex

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/opcspace/codexui/redesign-codex-ui
Any agent
npx skills add opcspace/CodexUI --skill redesign-codex-ui
Clone the repo
git clone --depth 1 https://github.com/opcspace/CodexUI

Made for: Claude Code, Codex.

Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,235 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 $0.00146 $0.03235
Opus 5 $0.00073 $0.01618
Sonnet 5 $0.00029 $0.00647
Haiku 4.5 $0.00015 $0.00324

Measured 2d ago against content hash ec322074dcf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

redesign-codex-ui 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 2d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/apply_theme_to_source.py, scripts/audit_codex_ui.py, scripts/build_macos_sidecar.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/redesign-codex-ui/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redesign Codex UI

Transform the current Codex interface into a coherent, production-ready design. Treat reference images, personas, and style labels as design evidence—not as permission to replace working product behavior with a static mock.

Choose the input path

Accept any combination of:

  • Reference image: inspect composition, density, hierarchy, color, type, radius, elevation, icon treatment, and interaction cues.
  • Role or persona: translate the role into workflows, information priority, terminology, density, defaults, and accessibility needs.
  • Personal, idol, or character theme: build a coherent edition around user-supplied portraits, signatures, memorabilia, original characters, or licensed IP assets. Theme navigation, hero, capability cards, composer, profile, and microcopy—not only the palette.
  • Named style: translate adjectives, products, eras, brands, or designers into explicit visual rules. Recreate principles, not protected logos, illustrations, or pixel-identical branded assets.
  • Open brief: infer a suitable direction from the existing product and state assumptions before implementation.

Apply this precedence when inputs conflict:

  1. Explicit functional and accessibility requirements
  2. Explicit user corrections and exclusions
  3. Reference image structure and visual evidence
  4. Persona workflow needs
  5. Named style cues
  6. Existing interface conventions

Read references/input-translation.md when the request includes a reference image, persona, or named style. Do not ask for information that can be inferred safely from the repository or supplied image.

Read references/personal-theme-packages.md when the request resembles a fan edition, celebrity skin, character theme, collectible interface, scrapbook interface, or deeply personalized Codex. Treat supplied identity assets as content with provenance and permissions, not as generic decoration.

Use assets/theme-library/default-identity.json and the transparent assets/default-identity/opcspace-ip-avatar.png as the default identity when the user supplies no IP image. Treat it as the OPCspace starter identity, not as a mandatory brand lock. If the user supplies another image, create a separate replacement profile with scripts/create_identity_profile.py; never overwrite the bundled default asset.

Read the full file on GitHub · 205 lines

Files

What ships with it

39 files 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. 2d ago First seen · 205 lines · 146 tokens per session scan A ec322074dcf9

Subscribe to this mod's changes

redesign-codex-ui is a skill published in the GitHub repository opcspace/CodexUI (11 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 3,235 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

female-portrait-director

Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter…

liyue-aigc/female-portrait-director · 112 tokens

oil-frontend

用于实现、修改、重构或评审产品前端。当前任务涉及页面、组件、交互、表单、状态、数据流、Hook、类型、视觉层级、排版、颜色、圆角、阴影、图标、响应式、动效、改变可见结果的 CSS 或前端代码组织时自动触发。触发后先阅读 SKILL.md,按任务的主要决策只加载最小规则集。纯 CSS 语法、导入或类名修复且不改变界面结果时不触发;纯构建、部署、依赖升级、安全、后端任务,以及只解释前端概念而不处理项目实现的请求也不触发。.

oil-oil/oil-frontend · 159 tokens

fashion-campaign-production

Provider-independent production workflow for AI-assisted fashion campaigns, lookbooks, editorial fashion films, ecommerce/editorial hybrids, social cutdowns, virtual try-on assets, generated model/lifestyle ads, and retouched fashion visuals; use when an agent must plan, prompt, produce, review, localize, or deliver…

calesthio/generative-media-skills · 95 tokens

apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…

spree/spree · 80 tokens

photo-revival

Turn ordinary photos or everyday snapshots into poetic hand-drawn illustrations with large white-paper negative space, vivid localized color, subtle collage accents, and tiny handwritten captions. Use when a user wants a real photo reimagined as an illustration rather than filtered, beautified, or photorealistically…

dacnay816y62-hub/photo-revival · 64 tokens

unity-ui-art-and-motion-production

Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…

hoatv2211/GameStudio-CodexKIT · 83 tokens