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.
git clone --depth 1 https://github.com/tygwan/stitchkitWrote 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.
[](https://agentmods.dev/agents/tygwan/stitchkit/design-explorer)<a href="https://agentmods.dev/agents/tygwan/stitchkit/design-explorer"><img src="https://agentmods.dev/badge/agents/tygwan/stitchkit/design-explorer/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.
<a href="https://agentmods.dev/agents/tygwan/stitchkit/design-explorer"><img src="https://agentmods.dev/badge/agents/tygwan/stitchkit/design-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.00417 |
| Opus 5.5 | $0.00010 | $0.00167 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 46 lines · 26 tokens per session scan A 8ac445c8be16
design-explorer is an agent published in the GitHub repository tygwan/stitchkit (7 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 417 once invoked, about $0.0001 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.
Other agents, from other repositories
canva-react-converter
Specialized agent for autonomous Canva-to-React component conversion. Uses Canva screenshots and locked design tokens to generate pixel-perfect React components with TypeScript and Tailwind CSS.
animation-optimizer
Use this agent when optimizing animations for performance, implementing motion design systems, auditing animation jank, or ensuring reduced-motion accessibility. Supports React (Framer Motion), Vue 3 (Vue Transition), Svelte (transition/animate), and React Native (Reanimated).
brand-guardian
Use this agent when establishing brand guidelines, ensuring visual consistency, managing brand assets, or evolving brand identity. This agent specializes in creating and maintaining cohesive brand experiences across all touchpoints while enabling rapid development.
conversation-designer
Use this agent when translating natural-language app descriptions into concrete design decisions. Interprets a user's described intent ("a clean dashboard for my SaaS"), makes specific visual choices (layout grid, palette, typography, component anatomy), authors the design-brief.json artifact, and generates the…
figma-react-converter
Specialized agent for autonomous Figma-to-React component conversion. Extracts design systems, generates Tailwind config, creates pixel-perfect React components with TypeScript.
ui-designer
Use this agent when creating user interfaces, designing components, building design systems, or improving visual aesthetics. This agent specializes in creating beautiful, functional interfaces that can be implemented quickly within 6-day sprints.