okf-studio: Skill for Claude Code

.agents/skills/theme-colors/SKILL.md

theme-colors is a skill for Claude Code, Codex from saschb2b/okf-studio. It costs 146 tokens per session (1,366 once invoked), scanned A, original, MIT.

A UI code checker that requires every color to come from a shared theme. A theme stores named roles such as primary, error, background, and text, so components use those roles instead of writing color values directly.

In plain words
What is it for?
Use it when writing or reviewing interface code to find hex, RGB, HSL, OKLCH, and named CSS colors. It replaces them with theme tokens and uses the theme's alpha helper for transparency.
Why use it?
Scattered color values make brand changes, dark mode, and consistent states harder to manage. Centralizing colors also avoids different components using slightly different values for the same purpose.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is saschb2b/okf-studio's own configuration. It tells Claude Code and Codex how to work on okf-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything okf-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saschb2b/okf-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saschb2b/okf-studio/main/.agents/skills/theme-colors/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/saschb2b/okf-studio

Made for: Claude Code, Codex.

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 theme-colors

README.md
[![agentmods](https://agentmods.dev/badge/skills/saschb2b/okf-studio/theme-colors/github.svg)](https://agentmods.dev/skills/saschb2b/okf-studio/theme-colors)
Your own site
<a href="https://agentmods.dev/skills/saschb2b/okf-studio/theme-colors"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/theme-colors/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 theme-colors

Your own site · 80×15
<a href="https://agentmods.dev/skills/saschb2b/okf-studio/theme-colors"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/theme-colors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,366 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 $0.00146 $0.01366
Opus 5.5 $0.00058 $0.00546
Sonnet 5.5 $0.00029 $0.00273
Haiku 4.5 $0.00015 $0.00137

Measured 3d ago against content hash abd7bbdbb729, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

theme-colors 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 3d 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.

.agents/skills/theme-colors/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Theme Colors

Rule

Every color comes from the theme. No hex literals, no rgba() strings, no scattered values.

A theme defines colors by role (primary, secondary, error, surface, text) once, in one place. Components reference the role, not the value. Brand changes update one file. Dark mode is the same theme with different values. Components derive their own hover, focus, and pressed transparencies from the role color via the alpha() helper.

The most common failure mode in LLM-generated UI is hex codes sprinkled through component files (color: "#3B82F6", bgcolor: "#1E293B", background: "rgba(255,255,255,0.5)"). Training corpora are dominated by tutorial code that hardcodes colors. The defaults skew wrong.

The vocabulary, 10 roles

Role Meaning Used for
primary Main brand color Main buttons, active tabs, key highlights
secondary Complementary accent Switches, FABs, selection controls
error Something wrong or destructive Error messages, delete buttons
warning Caution, not yet an error Warning banners, risky-action confirmations
info Neutral information, no urgency Tooltips, info badges, help text
success Positive outcome Success notifications, completion
background.default Page background ("the desk") The app's base background
background.paper Elevated surface ("paper on the desk") Cards, dialogs, dropdowns, menus, drawers
text.primary Main text, high emphasis Headings, body text
text.secondary De-emphasized text Captions, timestamps, helper text

Each role auto-derives .light, .dark, and .contrastText. Use the defaults; override only with a specific contrast or design reason.

Default behavior when writing UI

Do this:

<Box sx={{ color: "text.primary", bgcolor: "background.paper" }}>
  <Button color="primary">Save</Button>
</Box>

Not this:

<Box sx={{ color: "#1E293B", bgcolor: "#FFFFFF" }}>
  <Button sx={{ bgcolor: "#3B82F6" }}>Save</Button>
</Box>

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 146 tokens per session scan A abd7bbdbb729

Subscribe to this mod's changes

theme-colors is a skill published in the GitHub repository saschb2b/okf-studio (47 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 1,366 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-23.