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 skills add gabelul/stitch-kit --skill stitch-mcp-get-screengit clone --depth 1 https://github.com/gabelul/stitch-kitWrote 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/skills/gabelul/stitch-kit/stitch-mcp-get-screen)<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-mcp-get-screen"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-mcp-get-screen/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/skills/gabelul/stitch-kit/stitch-mcp-get-screen"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-mcp-get-screen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.01141 |
| Opus 5 | $0.00019 | $0.00571 |
| Sonnet 5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
stitch-mcp-get-screen 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch MCP — Get Screen
Retrieves the full output of a Stitch-generated screen: the HTML source code URL and the screenshot image URL. This is the gateway between Stitch design and framework conversion.
Critical prerequisite
Only use this skill when the user explicitly mentions "Stitch".
If you already have both projectId AND screenId, call this directly — do not call get_project first.
When to use
- After
list_screenshas returned a screenId - User provides a Stitch screen URL and wants to convert it to code
- Retrieving assets for any conversion skill: Next.js, Svelte, HTML, React Native, or SwiftUI
Step 1: Parse IDs from context
The user may provide the screen reference in different formats:
| Input format | → projectId | → screenId |
|---|---|---|
projects/123/screens/456 |
123 |
456 |
https://stitch.withgoogle.com/projects/123?node-id=456 |
123 |
456 |
| Separate numeric IDs already known | Use as-is | Use as-is |
Step 2: Call the MCP tool
get_screen is mid-migration: name is the current identifier and takes the full resource path, while projectId and screenId are marked deprecated but are still required. Send all three.
{
"name": "get_screen",
"arguments": {
"name": "projects/3780309359108792857/screens/88805abc123def456",
"projectId": "3780309359108792857",
"screenId": "88805abc123def456"
}
}
The prefix rule differs per field, which is the whole reason this wrapper exists:
✅ name: "projects/3780309359108792857/screens/88805abc123def456"
❌ name: "88805abc123def456"
✅ projectId: "3780309359108792857"
❌ projectId: "projects/3780309359108792857"
✅ screenId: "88805abc123def456"
❌ screenId: "screens/88805abc123def456"
nameis the full path; the other two are bare. Omittingnamefails — it's required despite the deprecated pair still being mandatory too.
Output schema
{
"name": "projects/3780309359108792857/screens/88805abc123def456",
"htmlCode": {
"downloadUrl": "https://storage.googleapis.com/stitch-output/..."
},
"screenshot": {
"downloadUrl": "https://storage.googleapis.com/stitch-screenshots/..."
},
"figmaExport": {
"downloadUrl": "https://storage.googleapis.com/stitch-figma/..."
},
"width": 390,
"height": 844,
"deviceType": "MOBILE"
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 126 lines · 38 tokens per session scan A 069bc2b0e45b
stitch-mcp-get-screen is a skill published in the GitHub repository gabelul/stitch-kit (44 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,141 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
kit-montar
Monta um site novo combinando peças já validadas do acervo pessoal do usuário — templates, design systems, componentes, animações, menus, prompts e receitas — em vez de gerar tudo do zero. Acervo vazio: constrói do zero e oferece guardar. Recebe o briefing, decide cor e tipografia antes da identidade, pergunta que…
kit-buscar
Consulta o acervo pessoal de sites do usuário — o que ele já guardou: templates rodáveis, design systems com paleta e tipografia, componentes de UI e de IA, animações de scroll, texto e menu, efeitos WebGL, prompts de página inteira e receitas de composição que já deram certo. Responde "o que eu já tenho pronto pra…
kit-cor
Define a paleta do site como decisão, não como consequência de ter escolhido um design system. Faz as perguntas que determinam cor (o que a marca promete, o que o setor já usa, para onde o olho tem que ir, o que ela NÃO pode parecer), monta a paleta por papel — fundo, tinta, superfície, acento — mede o contraste de…
kit-tipo
Define a tipografia do site como decisão — e, principalmente, resolve se dá para ENTREGAR. Confere licença (site de marca paga por tipo, e acervo montado a partir de site de marca vem cheio de fonte comercial que não se pode servir), propõe substituto livre com critério de desenho, monta o par display + corpo, gera a…
stitch-react-native
Convert Stitch HTML designs into React Native screens, or sync existing native components to updated Stitch designs, using native primitives, StyleSheet rules, and mobile platform checks.