mk:stitch

mk:stitch is a skill for Claude Code from ngocsangyem/MeowKit. It costs 53 tokens per session (1,549 once invoked), scanned A, original, MIT.

A design generator that creates new user-interface concepts from text prompts and exports HTML, Tailwind code, screenshots, and handoff notes.

In plain words
What is it for?
Use it to explore original UI directions and pass the resulting design materials to an implementation workflow.
Why use it?
It gives teams a visual starting point when designing a new interface from a written idea.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to explore original UI directions and pass the resulting design materials to an implementation workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ngocsangyem/meowkit/stitch
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.

Any agent
npx skills add ngocsangyem/MeowKit --skill stitch
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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.

agentmods badge for mk:stitch

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/stitch/github.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/stitch)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/stitch"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/stitch/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.

agentmods 80×15 button for mk:stitch

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/stitch"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/stitch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01549
Opus 5.5 $0.00021 $0.00620
Sonnet 5.5 $0.00011 $0.00310
Haiku 4.5 $0.00005 $0.00155

Measured 2mo ago against content hash a0de4333efda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mk: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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/stitch-api-call.ts, scripts/stitch-quota.ts, scripts/stitch-write-output.ts), 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.

.claude/skills/stitch/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch — AI Design Generation

Generate high-fidelity UI designs from text prompts. Export Tailwind/HTML, PNG screenshot, and DESIGN.md for handoff to mk:frontend-design.

Use only for a novel, text-prompt design. Existing design sources belong to mk:figma or mk:frontend-design.

Setup and guard

Set STITCH_API_KEY in the project env file, then install the scripts once:

cd .claude/skills/stitch/scripts && npm install

Run the prerequisite check before any API command; it fails before a network request if the key or tsx is unavailable. Full setup, optional variables, and MCP setup: references/stitch-setup.md.

Fail-Closed Gate

Before any script runs, verify both prerequisites:

# Key gate
[ -z "$STITCH_API_KEY" ] && { echo "[X] STITCH_API_KEY not set — add it to the project env file"; exit 1; }

# tsx gate
npx tsx --version 2>/dev/null || { echo "[X] tsx not found — run: cd .claude/skills/stitch/scripts && npm install"; exit 1; }

stitch-api-call.ts also checks STITCH_API_KEY as its first action before any Stitch SDK call. If the key is unset the script exits 1 immediately — no network request is made.

Quick Start

# 1. Check quota
npx tsx .claude/skills/stitch/scripts/stitch-quota.ts check

# 2. Generate (API call only — returns JSON with screenId + imageUrl)
npx tsx .claude/skills/stitch/scripts/stitch-api-call.ts \
  generate "A checkout page with cart summary and payment form"

# 3. Export + write files (pipe: API call → schema-validate → write to disk)
npx tsx .claude/skills/stitch/scripts/stitch-api-call.ts export <screen-id> | \
  npx tsx .claude/skills/stitch/scripts/stitch-write-output.ts

Commands

Task Command / contract
Check quota npx tsx .claude/skills/stitch/scripts/stitch-quota.ts check
Generate npx tsx .claude/skills/stitch/scripts/stitch-api-call.ts generate "<prompt>" — returns screenId, projectId, imageUrl, and quota data
Export npx tsx .claude/skills/stitch/scripts/stitch-api-call.ts export <screen-id> | npx tsx .claude/skills/stitch/scripts/stitch-write-output.ts

Read the full file on GitHub · 146 lines

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.

  1. 2mo ago First seen · 146 lines · 53 tokens per session scan A a0de4333efda

Subscribe to this mod's changes

mk:stitch is a skill published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 1,549 once invoked, about $0.0002 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 2026-09-03.

Related

mk:stitch compared with skills from other repositories

mk:stitch next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mk:stitchngocsangyem/MeowKitSkill155d agoMITA53Claude Code
stitch-design-systemgabelul/stitch-kitSkill483mo agoApache-2.0A47Claude Code
stitch-a11ygabelul/stitch-kitSkill483mo agoApache-2.0A43Claude Code
stitch-animategabelul/stitch-kitSkill483mo agoApache-2.0A39Claude Code
web-prototypenexu-io/open-designSkill106kyesterdayApache-2.0A59Claude Code, Codex
anti-slop-designsickn33/agentic-awesome-skillsSkill49kyesterdayMITA34Claude Code
velar-luxury-real-estatenexu-io/open-designSkill106kyesterdayApache-2.0A119Claude Code, Codex