design-system

design-system is a skill for Claude Code, Codex from fusengine/agents. It costs 31 tokens per session (2,050 once invoked), scanned C, original, MIT.

A starting guide for defining a design system: the shared rules for colors, typography, spacing, and visual tokens in a product. It also defines the required structure and checks for the design-system.md file.

In plain words
What is it for?
Use it at the beginning of a design task, before selecting or reviewing colors, type styles, or spacing. It routes work to the guides for websites, app screens, and mobile interfaces.
Why use it?
It gives later design work a consistent foundation instead of choosing visual values separately for each screen. It also makes the design-system file conform to the expected format.

Skill for Claude CodeCodex

Part of the fuse-design plugin — 9 skills, 5 commands, 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/fusengine/agents/design-system
Any agent
npx skills add fusengine/agents --skill design-system
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Or install fuse-design, the plugin that ships this one along with the rest of its 9 skills, 5 commands, 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 design-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/fusengine/agents/design-system.svg)](https://agentmods.dev/skills/fusengine/agents/design-system)
Your own site
<a href="https://agentmods.dev/skills/fusengine/agents/design-system"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-system.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,050 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00031 $0.02050
Opus 5 $0.00015 $0.01025
Sonnet 5 $0.00006 $0.00410
Haiku 4.5 $0.00003 $0.00205

Measured yesterday against content hash c3d51b350bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

design-system scanned grade C with 1 finding 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 yesterday.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Grounding: grounding-corpus.md §B (thresholds), §H (kept anchors); harness-contract.md invariant #2 (design-system.md format) + #3 (this file's read-path triggers harness phase 1). -->
plugins/design-expert/skills/design-system/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Also defines the canonical output format of design-system.md — the file the harness gates on — including its 4 hard requirements (the ## Design Reference heading, a real inspiration URL, at least one chroma-positive OKLCH token, and the hard-forbidden font exclusions).

This is routing step 1 of design-method/SKILL.md: read it before design-web, design-webapp, design-ios, or design-android, and before picking or auditing a single color/type/spacing value.

Design System — Token Core

Single source for token strategy — not values, values live in references/*.md and are read from there, never re-derived here. design-method/SKILL.md reads this file unconditionally as routing step 1, once per task, before dispatching to any move or target skill — that read is also what advances the harness past phase 0. If a design question is purely about a token (a color, a type pair, a spacing value) this file plus its reference index already answers it; otherwise continue back into design-method's routing.

Color strategy

  • OKLCH only for new tokens: oklch(L% C H). Never hex/HSL/RGB for anything you're defining fresh (existing legacy tokens in an inherited codebase are a different problem — don't rewrite what wasn't asked for).
  • Neutrals — tint every neutral toward the brand hue, chroma 0.005–0.015. Never a pure gray (chroma 0), never #000/#fff.
  • Accent commitment — pick the strategy BEFORE picking hues:
    • Restrained — tinted neutrals + one accent ≤10% of surface. Product register default.
    • Committed — one saturated color carries 30–60% of surface. Brand register default.
    • Full palette (3–4 named roles) / Drenched (surface IS the color) — brand campaigns, product data-viz. See design-method/references/register/brand.md §4 and register/product.md §1 for which strategy each register defaults to and when to deviate.
  • Reduce chroma as lightness approaches 0 or 100 — high chroma at the extremes reads garish.
  • Mechanics: references/oklch-system.md. Concrete per-sector values: references/sector-palettes.md. Contrast floors: references/contrast-ratios.md — WCAG AA 4.5:1 body text / 3:1 large text + UI components (AAA 7:1 where feasible).

Read the full file on GitHub · 138 lines

Files

What ships with it

34 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. yesterday First seen · 138 lines · 31 tokens per session scan C c3d51b350bbe

Subscribe to this mod's changes

design-system is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 2,050 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.