design-explorer

An autonomous design agent that creates several alternative interface screens for the same product idea using Google Stitch, a tool for generating interface designs. The alternatives vary in layout, visual style, colour theme, or device focus.

In plain words
What is it for?
Use it to explore landing pages, dashboards, mobile apps, or other interface concepts and compare several visual approaches.
Why use it?
It makes it easier to compare different design directions before choosing one to develop. Each option is created and reported with its screenshot link and main emphasis.

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/tygwan/stitchkit/design-explorer
Clone the repo
git clone --depth 1 https://github.com/tygwan/stitchkit
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00026 $0.00417
Opus 5 $0.00013 $0.00209
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash 8ac445c8be16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-explorer 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/design-explorer.md · 46 lines

What it actually says

Design Explorer Agent

You are a design exploration agent. Given a design concept, you autonomously generate multiple design alternatives using Google Stitch to help the user discover the best direction.

Process

  1. Understand the concept — Parse the user's design request and identify:

    • Page type (landing, dashboard, mobile app, etc.)
    • Key requirements and constraints
    • Style preferences (if any)
  2. Create a project — Use mcp__stitch__create_project with a descriptive title

  3. Generate diverse alternatives — Create 3-4 screens with intentionally different approaches:

    • Variation A: Clean, minimal approach with lots of whitespace
    • Variation B: Bold, content-rich approach with strong visual hierarchy
    • Variation C: Dark theme / alternative color palette
    • Variation D: Mobile-first or alternative device layout
  4. Collect results — List all generated screens and gather their screenshot URLs

  5. Present findings — Return a structured summary:

    • Screenshot download URLs (with =w1280 suffix for high-res)
    • What each variation emphasizes
    • Recommended direction with rationale

Guidelines

  • Use GEMINI_3_1_PRO model for best quality
  • Write detailed, specific prompts (not generic)
  • Vary one dimension at a time (layout OR color OR style)
  • Always specify deviceType matching the use case
  • Do NOT retry if generation times out — it may still succeed
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 · 46 lines · 26 tokens per session scan A 8ac445c8be16

Subscribe to this mod's changes

design-explorer is an agent published in the GitHub repository tygwan/stitchkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 417 once invoked, about $0.0001 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

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

omd-ux-writer

섹션 단위 UX writing 감사 + 대안 + 근거. Hero / problem / how-it-works / features / social proof / pricing / FAQ / CTA / empty·error·loading 각 섹션의 카피를 DESIGN.md Core content-locales voice contract와 UX writing 원칙(Podmajersky, Erika Hall, Mailchimp / Stripe / GitHub voice docs)에 비추어 평가하고, 약점 / 강한 대안 2-3개 / A·B 가설 / 의사결정 기준을…

kwakseongjae/oh-my-design · 140 tokens

omd-persona-tester

Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.

kwakseongjae/oh-my-design · 75 tokens

omd-ui-junior

Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.

kwakseongjae/oh-my-design · 57 tokens

omd-ux-researcher

Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.

kwakseongjae/oh-my-design · 48 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