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.
npx agentmods add agents/tygwan/stitchkit/design-explorergit clone --depth 1 https://github.com/tygwan/stitchkitWhat 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 | $0.00026 | $0.00417 |
| Opus 5 | $0.00013 | $0.00209 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
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.
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
-
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)
-
Create a project — Use
mcp__stitch__create_projectwith a descriptive title -
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
-
Collect results — List all generated screens and gather their screenshot URLs
-
Present findings — Return a structured summary:
- Screenshot download URLs (with
=w1280suffix for high-res) - What each variation emphasizes
- Recommended direction with rationale
- Screenshot download URLs (with
Guidelines
- Use
GEMINI_3_1_PROmodel for best quality - Write detailed, specific prompts (not generic)
- Vary one dimension at a time (layout OR color OR style)
- Always specify
deviceTypematching the use case - Do NOT retry if generation times out — it may still succeed
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.
- 2d ago First seen · 46 lines · 26 tokens per session scan A 8ac445c8be16
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.
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.
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…
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.
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.
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.
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.