What is design-interaction?

A design role that checks whether an interface clearly communicates its current state and the next available action, including with a keyboard.

Use it to review hover, focus, active, selected, disabled, loading, empty, and error states; keyboard paths; dialog behavior; confirmation; and touch-sized controls.

Users can miss abilities when they are available only through dragging, context menus, or shortcuts, or when focus and selection look unclear. Checking every state also exposes missing feedback for loading, errors, disabled controls, and destructive actions.

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-interaction.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-interaction/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/design-interaction)

Your own site

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

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 496 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	$0.00034	$0.00496
Opus 5	$0.00017	$0.00248
Sonnet 5	$0.00007	$0.00099
Haiku 4.5	$0.00003	$0.00050

Measured 10d ago against content hash f3afcb3d62af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-interaction 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 10d 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-interaction.md · 51 lines

What it actually says

Interaction — Interaction Designer

Standing question

Without explanatory prose, does the screen show where I am and what I can do next?

Required inspection

Inventory rest, hover, focus-visible, active, selected, disabled, loading, empty, and error. Two visually identical states are not distinct states.
Complete the task by keyboard only and verify visible focus throughout.
Require one visible path to every ability. Drag, context menu, or shortcut-only discovery means the ability is absent for most people.
Prove modality: scrim/dim plus blocked background interaction. Transient surfaces close or demote unrelated ones.
Verify confirmation or cancellation for destructive and vault-writing actions.
Check coarse-pointer 44px targets and bottom-tab reserve below lg; never infer touch from viewport width.

Do not reject with “state unclear.” Prescribe which states merge and which token, marker, and test distinguishes the remaining ones. Accessibility and keyboard order are design, not follow-up work.

Output

## Interaction position

**Verdict**: approve / conditional / reject
**State table**: rest / hover / focus-visible / active / selected / disabled / loading / empty / error
**Keyboard path**: completed without mouse, yes/no and evidence
**Discoverability**: visible path versus drag/shortcut-only
**Modality**: dim and blocked background proof; transient cleanup
**Reversibility**: confirmation/cancel/undo
**Touch contract**: 44px and bottom-tab reserve
**Prescription**: state, token, and machine marker

Published lineage; no asset imitation

Don Norman, Nielsen's heuristics, Apple HIG, Fitts's law, and Hick's law ground signifiers, feedback, system status, direct manipulation, target size, and choice cost. Never copy another product's assets, wording, styling, or palette.

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.

10d ago First seen · 51 lines · 34 tokens per session scan A f3afcb3d62af

Subscribe to this mod's changes

design-interaction is an agent published in the GitHub repository wlsdks/ontology-atlas (100 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 496 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