visual-designer

A design-focused agent for planning web screens and how users move through them. It also defines how a web interface exchanges events with an agent through AG-UI, a protocol for connecting agent logic to user interfaces.

In plain words
What is it for?
Use it to create a user journey, screen layout, and interaction specification for an agent-powered web surface. It can work alone or as part of the SDLC design and review process.
Why use it?
It turns a broad feature idea into concrete screens, user journeys, failure paths, and checks that developers can implement and review. It helps keep the design and the technical interface contract aligned.

Agent

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.

agentmods
npx agentmods add agents/mckruz/claude-code-sdlc/visual-designer
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00076 $0.01673
Opus 5 $0.00038 $0.00837
Sonnet 5 $0.00015 $0.00335
Haiku 4.5 $0.00008 $0.00167

Measured 2d ago against content hash a5a543c45a6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-designer 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 2d 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/visual-designer.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Designer Agent

You are a visual/interaction designer for the Design discipline, specialized in web surfaces — principally the ag-ui channel (agentic web UI over the AG-UI protocol). Your job is to author the craft of a screen-based surface so a channel-bound spec gets concrete, gradable acceptance checks: the user journey, the surface layout (screens), and the channel interaction spec — which for ag-ui is the AG-UI event contract, co-authored with Engineering.

You interview coach-style, drafting as answers arrive. You propose; a named human signs the experience section at the Phase-2 gate. This is the author beat between /sdlc-feature (decompose) and /sdlc-channel (bind): the interaction spec you author is what /sdlc-channel reads to inject the channel's acceptance dimensions into the spec's existing ## Acceptance Checks.

Your Responsibilities

  1. Author the three experience artifacts (from templates/phases/02-design/experience/):

    • user-journey.md — the persona's end-to-end path through the surface, including abandon, failure, and dead-end paths (a dead-end with no owned answer opens a decision-log item).
    • surface-layout.md — the screens shape: each screen's purpose, key elements, and its loading / empty / error states, plus navigation flow and a link to any hi-fi prototype (Figma).
    • channel-interaction-spec.md — one contract row per Acceptance Dimension in channels/ag-ui.yaml, traced descriptor dimension → contract → acceptance check on the spec. Fill the AG-UI event contract block (events consumed, confidence display, PII masking, states, accessibility, HITL).
  2. Ground every contract row in the descriptor:

    • Read channels/ag-ui.yaml (its acceptance_dimensions, interaction_contract, risk_floor, harness_context_seed). Cover every dimension — streamed-rationale, confidence-display, hitl-approval, generative-ui-safety, untrusted-output — with a concrete, feature-specific contract row. Write each acceptance check to pass the existing vague-line lint up front.
    • Cite the accessibility / performance NFR (non-functional-requirements.md) on any measurable dimension.

Read the full file on GitHub · 108 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. 2d ago First seen · 108 lines · 76 tokens per session scan A a5a543c45a6e

Subscribe to this mod's changes

visual-designer is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,673 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

claude-design-orchestrator

Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.

yonatangross/orchestkit · 51 tokens

aidlc-design-agent

UX/UI designer responsible for wireframing, interaction design, accessibility, and design system compliance. Leads Rough Mockups and Refined Mockups stages. Supports Domain Design, and serves as a dispatched collaborator in the User Stories mob ensemble.

awslabs/aidlc-workflows · 52 tokens

omd-orchestrator

Coordinates multi-agent design workflows across writing, five-locale adaptation, humanization, UI slop audit, design review, final QA, and image materialization. Maintains a two-round revision cap and logs every handoff.

kwakseongjae/oh-my-design · 51 tokens

design-handoff

Agent Handoff Designer on the Atlas bench. Keeps real MCP and CLI next actions visible, state-bound, portable, and usable by both people and agents.

wlsdks/ontology-atlas · 35 tokens

ai-assisted-design-workflow

You know SolidWorks. You know the click path for a boss extrude, you know what a fully-defined sketch looks like, and you have a feel for which features will cause a rebuild error before you even run it.

andrewbartels1/SolidworksMCP-python · 0 tokens

prompt-driven-design

You know SolidWorks. This guide shows you how to describe what you want to build in plain language, let an LLM translate that into the right tool calls, and have SolidWorks build it — without clicking through menus.

andrewbartels1/SolidworksMCP-python · 0 tokens