A guide for operating Google Stitch through an existing connection, including creating, editing, varying, importing, exporting, and synchronising Stitch screens. It can also help turn Stitch screens into React code.

Use it to manage Stitch projects and screens, maintain a Stitch design system, or convert Stitch screens into React.

It keeps Stitch screen work aligned with the application's existing design decisions and technical structure.

stitch — Skill for Claude Code and Codex by Dannykkh: A guide for operating Google Stitch through an existing…

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 skills/dannykkh/skill-olympus/stitch

Any agent

npx skills add Dannykkh/skill-olympus --skill stitch

Clone the repo

git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code, Codex.

Or install skill-olympus, the plugin that ships this one along with the rest of its 95 skills, 6 commands, 42 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dannykkh/skill-olympus/stitch.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/stitch)

Your own site

<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/stitch"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/stitch.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,053 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.

Model	Per session	Once invoked
Fable 5.1	$0.00077	$0.02053
Opus 5	$0.00039	$0.01026
Sonnet 5	$0.00015	$0.00411
Haiku 4.5	$0.00008	$0.00205

Measured 2d ago against content hash e7a4edbb38a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

stitch 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/fetch_stitch_asset.py, scripts/upload_to_stitch.py, scripts/validate_stitch_state.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/stitch/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch

Treat Stitch as a design execution backend. Keep product structure, visual direction, and design policy in Aphrodite; use this skill to translate those decisions into Stitch operations and code artifacts.

Boundary

Let design-plan (/aphrodite) own discovery, IA, layout blueprints, and the root DESIGN.md.
Let Stitch own remote project/screen operations and .stitch/ runtime state.
Let the existing application architecture own routing, state, data, and component conventions.
Use standalone Stitch mode only when the user explicitly wants direct Stitch work without Aphrodite.

Never invent a visual direction inside this skill when DESIGN.md or docs/design-refs/ exists. Compile those artifacts into Stitch inputs.

Preflight

Inspect the available tools and identify the Stitch MCP namespace by capability, not by a hard-coded prefix.
Stop and report the missing dependency if no Stitch MCP tools are available. Never fabricate project IDs, screen IDs, URLs, or tool results.
Read references/mcp-contract.md completely before any Stitch MCP call.
Read the project root DESIGN.md and relevant docs/design-refs/ artifacts before generating or editing a screen.
Check .stitch/metadata.json before remote lookup. Validate it with:

python <STITCH_SKILL_DIR>/scripts/validate_stitch_state.py .stitch/metadata.json

Resolve <STITCH_SKILL_DIR> to the directory containing this SKILL.md; do not assume the skill is installed inside the target project.

Classify the action:
- Read-only: list/get projects, retrieve screens, download artifacts, compare state.
- Remote mutation: create/edit/vary/apply a design system.
- Sensitive upload: send a local image, HTML file, or DESIGN.md to Stitch.
Treat the user's explicit request to create/edit/vary as authorization for that scoped remote mutation. Before a sensitive upload, still show the exact project, files, types, and sizes and obtain confirmation.

Read the full file on GitHub · 140 lines

Files

What ships with it

9 files 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.

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.

2d ago First seen · 140 lines · 77 tokens per session scan A e7a4edbb38a3

Subscribe to this mod's changes

stitch is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 2,053 once invoked, about $0.0004 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 2026-09-03.

Design and UX Frontend React agent-orchestration ai-agent ai-automation ai-coding ai-tools claude-code

generic-react-feature-developer

Guide feature development for React applications with architecture focus. Covers Zustand/Redux patterns, IndexedDB usage, component systems, lazy loading strategies, and seamless integration. Use when adding new features, refactoring existing code, or planning major changes.

travisjneuman/.claude · 53 tokens

generic-react-ux-designer

Professional UI/UX design expertise for React applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design…

travisjneuman/.claude · 69 tokens

generic-react-code-reviewer

Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…

travisjneuman/.claude · 71 tokens

generic-react-design-system

Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.

travisjneuman/.claude · 59 tokens

react-patterns

// Good interface UserCardProps { user: User; onSelect: (id: string) => void; variant?: "compact" | "full"; }.

halflength-ampleness75/claude-code-recipes · 0 tokens

delight

Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful.

rwliebs/Dossier · 28 tokens