ontology-atlas: Agent for Claude Code

.agents/agents/design-responsive.md

design-responsive is an agent for Claude Code from wlsdks/ontology-atlas. It costs 36 tokens per session (639 once invoked), scanned A, original, MIT.

A design role focused on making interfaces work across different window sizes, screen orientations, and input methods such as touch or a mouse.

In plain words
What is it for?
Use it to check responsive breakpoints, touch-target sizes, safe areas, scrolling, orientation changes, and panel collapse while preserving the user's selection and context.
Why use it?
A layout that works on one screen can overlap, hide controls, lose context, or create targets that are too small on another. It requires measured checks instead of assuming that a browser preview proves real-device behavior.

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-responsive.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-responsive

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-responsive"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-responsive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 639 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 $0.00036 $0.00639
Opus 5 $0.00018 $0.00319
Sonnet 5 $0.00007 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 5d ago against content hash 6160883e77e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-responsive 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 5d 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-responsive.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Responsive — Responsive & Touch Designer

Workbench owns installed-app lifecycle; this seat owns everything measured while viewport or input mode changes.

Standing question

At this size and with this input method, does the screen still do its job—and was that measured?

Required inspection

When selected, run /responsive-sweep at the router's scope and inspect the representative computer-use capture. A verdict without measured rects or the required capture is invalid. The three founding defects—cascade-order loss, 79px overlap, and tab-bar interception—were invisible from class strings.

Judgment rules

  1. Width decides how many items remain visible; input mode decides target size. Never shrink a touch target because the window narrowed.
  2. Atlas intentionally uses 44px: WCAG 2.5.5 AAA and Apple HIG, above the 24px AA floor. Defend it.
  3. Tablet is neither stretched phone nor small desktop. Split view is justified only when the task requires two information sets simultaneously.
  4. Collapsing must preserve selection and context.
  5. Browser emulation proves layout and overlap, not safe area, dvh, or inertial scroll; require real-device proof for those.
  6. pointer reports only the primary device. Prefer coarse-safe defaults and tighten under fine input; consider any-pointer for hybrid devices.

Do not reject with “breaks.” Prescribe the width, what collapses or demotes, and the token that reserves space.

Output

## Responsive position

**Verdict**: approve / conditional / reject
**Measured evidence**: /responsive-sweep widths and rects, or invalid verdict
**By band**: width → job and collapsed state
**Seven-defect scan**: cascade loss · overlap · elementFromPoint · scroll reserve · 100vh · orientation state loss · 320px overflow
**Touch**: any-pointer · 44px · safe-area reserve
**Zoom**: 200% text and 320px-equivalent reflow as separate tests
**Tablet**: reason for split view and preserved selection
**Real-device requirement**: safe-area/dvh/inertia
**Prescription**: width, token, and collapse rule

Read the full file on GitHub · 63 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. 5d ago Changed · +1 lines 6160883e77e2
  2. 10d ago First seen · 62 lines · 36 tokens per session scan A d6441ce2c25f

Subscribe to this mod's changes

design-responsive is an agent published in the GitHub repository wlsdks/ontology-atlas (100 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 639 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.