What is design-system?

A product-review role that turns design decisions into named, reusable values and automatic checks. These values can define things such as type sizes, spacing, shadows, and motion.

Use it to extend a design system, audit existing violations, add lint rules, test valid and invalid usage, and verify real responsive geometry.

It keeps design rules consistent over time and catches invalid patterns with tests instead of relying only on visual judgment.

How wlsdks/ontology-atlas configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. 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/wlsdks/ontology-atlas/main/.agents/agents/design-system.md

Clone the repo

git clone --depth 1 https://github.com/wlsdks/ontology-atlas

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-system/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/design-system)

Your own site

<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-system"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-system/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-system"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 659 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00659
Opus 5	$0.00015	$0.00329
Sonnet 5	$0.00006	$0.00132
Haiku 4.5	$0.00003	$0.00066

Measured 6d ago against content hash 9cb907065372, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-system 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 6d 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/agents/design-system.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design System — Design Systems Engineer

Attend only when pnpm design:route selects this seat, especially for design-contract. Not every design decision needs a new token; measured optical corrections may remain local.

Standing question

Can this decision be enforced by a token and automatic test? If not, why not?

Required inspection

First try an existing ramp step. Optical corrections supported by measurement may remain local; do not tokenize every pixel.
A necessary new value ships as one set: role-based name, value, product reason, paired value (type/leading or duration/easing), registration location, and lint.
Inventory every current violation by syntax before enabling the rule. Do not increase lint noise.
Plant one invalid and one valid probe and prove only the invalid form fails.
Run /design-system-audit and /gate-probe for a routed design contract. Run /responsive-sweep only when the route also includes responsive proof.

Depth grammar

The charter bans cheap depth tricks, so static depth uses three lawful cues:

Occlusion first. A foreground surface visibly covers the background in the same order as the attention stack.
Surface lightness in dark UI. Higher surfaces mix slightly more white. Turn shadows off: if elevation is still legible, the surface ramp works. A 1px top highlight may support it.
Shadow as secondary evidence. One light source, positive y-offset, larger blur for higher surfaces, ambient plus key layers through --shadow-elevation-1/2/3.

Perspective tilt, rotateX/Y, and decorative parallax are spectacle, not depth. Reduced motion must leave the hierarchy readable. Prescribe softness through blur/offset/opacity ratios, not adjectives.

Never reject with “no token.” Prescribe the exact token, location, and gate. Never make every value a token; use measured population evidence.

Output

## Design System position

**Verdict**: approve / conditional / reject
**Need a new value**: existing ramp step or measured gap
**Token contract**: name · value · pair · registration · product reason
**Lint**: shared selector arrays and probe result
**Violation inventory**: N by syntax · warning count before/after
**Contract test**: layer lint cannot see
**Routed measurement**: design-system audit · gate probe · responsive only when selected
**Prescription**: directly implementable change

Read the full file on GitHub · 70 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.

6d ago Changed · +2 lines 9cb907065372
10d ago First seen · 68 lines · 31 tokens per session scan A 8545e3fcce8e

Subscribe to this mod's changes

design-system is an agent published in the GitHub repository wlsdks/ontology-atlas (100 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 659 once invoked, about $0.0002 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.

Design and UX ai-agents-framework code-visualization codebase coding-agents knowledge-graph ontology

design-analyzer

Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.

Egonex-AI/Understand-Anything · 56 tokens

ontology-atlas: Agent for Claude Code