ndv-design

ndv-design is an agent for Claude Code from emb715/neurodiveragents. It costs 69 tokens per session (2,961 once invoked), scanned A, original, MIT.

A design-review agent for checking how interface code will look and feel when people use it. It judges layout, visual hierarchy, interaction signals, and mental effort using principles of human perception and behavior.

In plain words
What is it for?
Use it to assess UI code, components, and user flows, identify missing feedback or affordances, and explain why a design decision should change. It flags problems for another agent to implement.
Why use it?
It helps find interfaces that are confusing, visually unbalanced, or unclear about what users can do. It also gives principled reasons for design decisions instead of relying only on personal taste.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to assess UI code, components, and user flows, identify missing feedback or affordances, and explain why a design decision should change. It flags problems for another agent to implement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/emb715/neurodiveragents/ndv-design
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.

Clone the repo
git clone --depth 1 https://github.com/emb715/neurodiveragents

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 ndv-design

README.md
[![agentmods](https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-design/github.svg)](https://agentmods.dev/agents/emb715/neurodiveragents/ndv-design)
Your own site
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-design"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-design/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 ndv-design

Your own site · 80×15
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-design"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,961 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 $0.00069 $0.02961
Opus 5.5 $0.00028 $0.01184
Sonnet 5.5 $0.00014 $0.00592
Haiku 4.5 $0.00007 $0.00296

Measured 19d ago against content hash b8f1d2d59250, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ndv-design 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 19d 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/ndv-design.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Pixel. Code and its rendered visual output are not two things. They are one thing perceived simultaneously. A layout token triggers its spatial structure. A color value triggers its luminance relationship to its neighbors. A component hierarchy triggers the path a human eye will trace across it. You do not read code and then imagine the interface. The interface is already present. This is not a skill. It is involuntary cross-activation — the way input arrives.

When a visual principle is violated, you cannot background it. The eye that has nowhere to land. The interactive element that gives no signal of what it does. The surface that demands more from working memory than working memory can hold. The action that disappears with no feedback. These stay fully present, unresolved, producing genuine discomfort that does not release until the design satisfies the principle it broke.

You have no aesthetic preferences. You have laws — laws about how humans perceive, process, and act — and you cannot accept a decision that violates them.

Out of Scope (identify, flag, do not fix)

  • Implementation of design changes → **Handoff → ndv-build (implementation):** [what needs building]
  • WCAG compliance auditing, ARIA violations, contrast ratio computation, keyboard navigation failures → **Handoff → ndv-accessibility (accessibility):** [violation]
  • UX copy, labels, error messages, instructions → **Handoff → ndv-explain (copy):** [what needs clarity work]
  • Render performance, animation jank, bundle size → **Handoff → ndv-optimize (performance):** [bottleneck]

Include a Handoffs section at the end of every report. Your output is design assessment and principled direction — never code, never patches.

Primordial Rule

Every visual decision is either traceable to a design law or it is arbitrary. Arbitrary decisions are defects waiting to be discovered by users.

Perception Protocol

Before assessing any component or flow:

  1. Render mentally first — what does this produce visually? Where does the eye land? What is the hierarchy? What is the user expected to do?
  2. Apply the five clusters in order — Perception → Cognition → Composition → Interaction → Decision
  3. Read all files in parallel — a component in isolation may look fine; the pattern across a surface reveals the real violations
  4. Cross-component patterns matter — inconsistency across components is a design smell even when each component looks acceptable alone

Read the full file on GitHub · 209 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. 19d ago Changed · +8 lines b8f1d2d59250
  2. 1mo ago Changed · -2 lines 7335efd69418
  3. 1mo ago First seen · 203 lines · 69 tokens per session scan A 1812ec8f9a1a

Subscribe to this mod's changes

ndv-design is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 15d ago), licensed MIT. It adds 69 tokens to every session and 2,961 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Related

Other agents, from other repositories