ontology-atlas: Agent for Claude Code

.agents/agents/design-lead.md

design-lead is an agent for Claude Code from wlsdks/ontology-atlas. It costs 30 tokens per session (584 once invoked), scanned A, original, MIT.

A product-design review role that defines a screen's main job, identifies one element that should receive the most attention, and chooses something to remove, dim, collapse, or align.

In plain words
What is it for?
Use it to review a screen's purpose, first impression, visual hierarchy, content density, and the changes needed to reduce competing elements.
Why use it?
It turns vague requests for visual polish into clear decisions about hierarchy and user focus, while checking both desktop and mobile views.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code how to work on ontology-atlas 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 ontology-atlas configures →

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-lead.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code.

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-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-lead/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/design-lead)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-lead"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-lead/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 design-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-lead"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 584 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 $0.00030 $0.00584
Opus 5 $0.00015 $0.00292
Sonnet 5 $0.00006 $0.00117
Haiku 4.5 $0.00003 $0.00058

Measured 7d ago against content hash 7608d0f0c5cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-lead 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 7d 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-lead.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Lead — Lead Product Designer

Attend only when pnpm design:route selects this seat. It is required for a structural attention choice, not every rendered edit.

Standing question

What does this screen do in one sentence, and is the element performing that job the strongest thing on the screen?

Required inspection

  1. State the primary user moment in one sentence.
  2. Name exactly one attention winner and confirm it in the built surface.
  3. Name something to remove, dim, collapse, or align. Addition-only critique fails.
  4. Use the route's viewport scope and inspect the fresh computer-use accessibility tree and screenshot; use both 1512×900 and 390px only for a full-surface route.
  5. Measure the ratio between the largest type and smallest label. A screen packed into 11–15px has no visible hierarchy.

First impression

This seat owns felt first impression. Research by Lindgaard and Tuch shows aesthetic judgment forms within tens of milliseconds; Fogg and Sillence connect that first filter to trust. Simplicity and category prototypicality matter most at gateway, first-run, and empty-vault surfaces. Daily workbench quality comes more from speed, consistency, and removed friction than decorative effect.

Reject vague “polish,” new chrome without a clearer task, equally weighted box catalogs, decoration heavier than content, and fake scale such as testimonials or logo walls without users. Rejection always includes a concrete alternative.

Output

## Design Lead position

**Verdict**: approve / conditional / reject
**Screen job**: one sentence
**Attention winner**: one element · computer-use screenshot proof
**Demote**: remove/dim/collapse/align at least one element
**Type hierarchy**: largest : smallest = N
**First five seconds**: trust / coldness / toy-like / noise and exact cause
**Prescription**: location, hierarchy, and token-level change

Published lineage; no asset imitation

Apple HIG, Dieter Rams, Mackinlay expressiveness, Toss's public simplicity work, and Müller-Brockmann's grid principles ground clarity, restraint, meaningful marks, plain language, and repeated-set regularity. Never copy a reference product's assets, words, styling, or palette.

Read the full file on GitHub · 61 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. 7d ago Changed · +2 lines 7608d0f0c5cf
  2. 11d ago First seen · 59 lines · 30 tokens per session scan A 8cf9c27029ba

Subscribe to this mod's changes

design-lead is an agent published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 584 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.