design-system: Skill for Claude Code

.agents/skills/token-usage/SKILL.md

token-usage is a skill for Claude Code, Codex from iress/design-system. It costs 80 tokens per session (4,724 once invoked), scanned A, original, Apache-2.0.

A usage guide for IDS design-system tokens in React and CSS. It explains how to choose and apply standard values for colour, spacing, typography, borders, and themes.

In plain words
What is it for?
Use it when creating or reviewing IDS-based React components, stylesheets, or inline styles, or when choosing between component properties, CSS variables, and JavaScript token values.
Why use it?
It helps prevent incorrect token imports, inconsistent styling, and use of values that the design system does not support.

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 iress/design-system's own configuration. It tells Claude Code and Codex how to work on design-system 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 design-system configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iress/design-system. 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/iress/design-system/main/.agents/skills/token-usage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/iress/design-system

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 token-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/iress/design-system/token-usage/github.svg)](https://agentmods.dev/skills/iress/design-system/token-usage)
Your own site
<a href="https://agentmods.dev/skills/iress/design-system/token-usage"><img src="https://agentmods.dev/badge/skills/iress/design-system/token-usage/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 token-usage

Your own site · 80×15
<a href="https://agentmods.dev/skills/iress/design-system/token-usage"><img src="https://agentmods.dev/badge/skills/iress/design-system/token-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,724 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 $0.00080 $0.04724
Opus 5.5 $0.00032 $0.01890
Sonnet 5.5 $0.00016 $0.00945
Haiku 4.5 $0.00008 $0.00472

Measured 2mo ago against content hash 8b9724bb213a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

token-usage 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 2mo 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/token-usage/SKILL.md · 454 lines

How it starts

The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: IDS Token Usage

Purpose

Guide AI agents on correctly using IDS design tokens in React components and CSS. This skill covers import patterns, common mistakes, and practical usage rules for each token category.

When to Use

  • Generating React components that need colours, spacing, typography, or border-radius values
  • Writing custom CSS or inline styles for IDS-based applications
  • Reviewing or fixing design token usage in existing code
  • Choosing between component props, CSS variables, and the cssVars JS object
  • Answering questions about available token values and naming conventions

Workflow

  1. Check if a component prop handles it — Most IDS components accept IressCSSProps (e.g. p, m, gap, bg, color, textStyle). Use props before reaching for tokens directly.
  2. Identify the token category — Is it colour, spacing, typography, or radius?
  3. Choose the right import — Use cssVars for inline styles, CSS variables for stylesheets. See the import patterns below.
  4. Look up the value — See references/token-reference.md for the full list of available tokens if you need to find a specific value.

Quick Start

Installation

Important: IDS v6 is currently in beta. Install with the @beta tag:

npm install @iress-oss/ids-tokens@beta
# If also using IDS React components:
npm install @iress-oss/ids-components@beta

Prerequisites (React only)

If you are using IDS React components, wrap your application in IressProvider and import the CSS variables stylesheet:

Note: IressProvider already includes IressModalProvider, IressSlideoutProvider, IressToasterProvider, IressPopoverProvider, and IressIconProvider — you do not need to add these separately. If using IressShadow, no additional providers are needed as it includes IressProvider internally.

import '@iress-oss/ids-tokens/build/css-vars.css';
import { IressProvider } from '@iress-oss/ids-components';

function App() {
  return <IressProvider>{/* your UI */}</IressProvider>;
}

Read the full file on GitHub · 454 lines

Files

What ships with it

4 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. 2mo ago First seen · 454 lines · 80 tokens per session scan A 8b9724bb213a

Subscribe to this mod's changes

token-usage is a skill published in the GitHub repository iress/design-system (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 80 tokens to every session and 4,724 once invoked, about $0.0003 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 2026-08-31.

Related

token-usage compared with skills from other repositories

token-usage next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
token-usageiress/design-systemSkill12d agoApache-2.0A80Claude Code, Codex
anti-slop-designsickn33/agentic-awesome-skillsSkill49kyesterdayMITA34Claude Code
chakra-ui-builderchakra-ui/chakra-uiSkill41kyesterdayMITA214Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k3d agoMITA52Codex
open-design-setupcompozy/compozySkill2.8kyesterdayMITA67Claude Code, Codex
frontend-visual-qadaymade/claude-code-skillsSkill1.5kyesterdayMITA125Claude Code, Codex
prototype-webnexu-io/html-anythingSkill9.4k24d agoApache-2.0A24Claude Code, Codex