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 skills/tygwan/stitchkit/stitch-setupnpx skills add tygwan/stitchkit --skill stitch-setupgit 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/skills/tygwan/stitchkit/stitch-setup)<a href="https://agentmods.dev/skills/tygwan/stitchkit/stitch-setup"><img src="https://agentmods.dev/badge/skills/tygwan/stitchkit/stitch-setup.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.01637 |
| Opus 5 | $0.00011 | $0.00818 |
| Sonnet 5 | $0.00004 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade B, and why
stitch-setup scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **User-level** | `~/.claude/settings.json` → `mcpServers` | Global MCP servers available everywhere | How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch, Figma & NanoBanana MCP Setup
Help the user install and configure Google Stitch, Figma, and NanoBanana MCP servers for Claude Code.
Usage
/stitch-setupor/stitch-setup all— Set up all three MCP servers (Stitch, Figma, NanoBanana)/stitch-setup stitch— Set up Stitch MCP only/stitch-setup figma— Set up Figma MCP only/stitch-setup nanobanana— Set up NanoBanana MCP only
Important: API Key Security
WARNING: API keys and access tokens are sensitive credentials. Follow these rules:
- NEVER commit API keys to git. Add
.envto.gitignore.- NEVER hardcode tokens directly in
.mcp.jsonif the project is public.- Use environment variables or
.envfiles for token storage.- Rotate tokens immediately if accidentally exposed.
- Use the minimum required permissions when generating tokens.
Setup Process
Google Stitch MCP
Stitch uses Google Cloud API key authentication via the official Google Stitch MCP server (HTTP type).
Step 1: Get a Google Cloud API Key
- Go to Google Cloud Console
- Create or select a project
- Navigate to APIs & Services → Credentials
- Click + CREATE CREDENTIALS → API key
- (Recommended) Click Edit API key to restrict it:
- Application restrictions: Set by HTTP referrer or IP
- API restrictions: Restrict to Stitch/Generative AI APIs only
- Copy the API key
Step 2: Configure Stitch MCP
Option A: Using environment variable (recommended for public repos)
Create a .env file in your project root (make sure it's in .gitignore):
GOOGLE_API_KEY=your-api-key-here
Add to .mcp.json:
{
"stitch": {
"type": "http",
"url": "https://stitch.googleapis.com/mcp",
"headers": {
"X-Goog-Api-Key": "your-api-key-here"
}
}
}
Or using environment variable:
{
"stitch": {
"type": "http",
"url": "https://stitch.googleapis.com/mcp",
"headers": {
"X-Goog-Api-Key": "${GOOGLE_API_KEY}"
}
}
}
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.
- 3d ago First seen · 227 lines · 22 tokens per session scan B 8527c6a469b1
stitch-setup is a skill published in the GitHub repository tygwan/stitchkit (5 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 1,637 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
figma-typings-audit
Upgrade @figma/plugin-typings and absorb what the new version exposes. Diffs the .d.ts between the installed and the target version (that package ships no changelog), sorts the changes into breakage / new API / silently-added fields, maps each onto the sandbox handlers, the hand-written Zod mirrors in shared, and the…
mcp-sdk-audit
Upgrade @modelcontextprotocol/server (the MCP TypeScript SDK v2) and prove the wire contract survived. The SDK is a runtime dependency whose breakage lands on the wire, not in the type checker — so this sorts each release by which SDK source files it touched (Figwright uses only the server + stdio slice of a…
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
figma-build
Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…
design-qa
빌드된 앱 화면을 실기기/시뮬레이터에서 캡처해 Figma 원본과 오버레이(50% 블렌드 + diff 히트맵 + figma|real 나란히 크롭 + 픽셀색 비교)로 대조하고, 코드 오차로 확정된 항목을 Figma 선언값으로 되짚어 스스로 보정하는 검증 루프. 비교·측정 엔진은 플랫폼 중립이고 캡처 계층만 플랫폼별이다(Android·iOS·Web 지원). 두 진입: ① codegen Step 7c 위임 호출, ② 직접 호출(/design-qa) — 프롬프트로 검증/보정 모드를 판별하고 Figma 링크 해소·현재 브랜치 빌드·캡처까지 스스로 오케스트레이션. "오버레이…
design-to-ui
Figma 디자인을 네이티브 UI(Android Compose/XML, iOS SwiftUI/UIKit)로 변환하는 7-Step 워크플로우. 노드 추출·디자인 컨텍스트·검증(Step 1·2·3·7)은 플랫폼 공통이고, 에셋(Step 4·5)과 코드 생성(Step 6)만 플랫폼별 reference로 분기한다. 에셋 A/B/C 분류, 동적 비주얼, project-design-system 위임, 플랫폼 에셋 파이프라인을 포함한다. Figma URL이나 UI 변환 요청 시 이 스킬을 사용하세요.