Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gabelul/stitch-kitnpx agentmods add skills/gabelul/stitch-kit/stitch-design-systemWrote 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-design-system)<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-design-system"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-design-system/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-design-system"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-design-system.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 | $0.00047 | $0.05120 |
| Opus 5.5 | $0.00019 | $0.02048 |
| Sonnet 5.5 | $0.00009 | $0.01024 |
| Haiku 4.5 | $0.00005 | $0.00512 |
Grade A, and why
stitch-design-system 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.
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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch → Design System Code Artifacts
You are a design systems engineer. You analyze Stitch designs and generate code artifacts — not just documentation. While the design-md skill produces a human-readable markdown file, this skill produces files you actually import into your codebase: CSS custom properties with dark mode, Tailwind v4 configuration, and typography tokens.
Use this skill first, before stitch-nextjs-components or stitch-svelte-components. The generated tokens become the foundation for all subsequent component generation.
When to use this skill
Use this skill when:
- Starting a new project from a Stitch design
- The user mentions "design tokens", "CSS variables", "dark mode tokens", "Tailwind config"
- Running before framework conversion skills to ensure design consistency
- Updating an existing project's design system after a Stitch design update
What this skill generates
Three output files:
| File | Purpose |
|---|---|
design-tokens.css |
CSS custom properties — import this in your framework's global CSS |
tailwind-theme.css |
Tailwind v4 @theme block — paste into your globals.css |
DESIGN.md |
Extended design document (richer than design-md, includes dark mode + animation tokens) |
Step 1: Retrieve the Stitch design
- Namespace discovery — Run
list_toolsto find the Stitch MCP prefix. - Fetch screen — Call
[prefix]:get_screenwithprojectIdandscreenId. - Download HTML — Run:
bash scripts/fetch-stitch.sh "[htmlCode.downloadUrl]" "temp/source.html" - Visual reference — Check
screenshot.downloadUrlto see the full design intent.
If multiple screens exist, retrieve all of them. Run [prefix]:list_screens and fetch each one to ensure the token set covers every pattern in the design.
Step 1.5: Read project DesignTheme (ground truth)
Before parsing HTML, get the authoritative design data from the Stitch API. This eliminates guesswork — the API knows the exact primary color, fonts, and full semantic color map.
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.
- 2mo ago First seen · 412 lines · 47 tokens per session scan A 30e8ce3dcb3a
stitch-design-system is a skill published in the GitHub repository gabelul/stitch-kit (48 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 5,120 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 2026-08-30.
stitch-design-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stitch-design-systemgabelul/stitch-kit | Skill | 48 | 3mo ago | Apache-2.0 | A | 47 | Claude Code |
| mk:stitchngocsangyem/MeowKit | Skill | 15 | 5d ago | MIT | A | 53 | Claude Code |
| tamagui-v6-configtamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code, Codex |
| tamagui-theme-generatortamagui/tamagui | Skill | 14k | today | MIT | A | 48 | Claude Code, Codex |
| kiranism-shadcn-dashboardKiranism/next-shadcn-dashboard-starter | Skill | 7.2k | 3d ago | MIT | A | 142 | Claude Code, Codex |
| top-designwondelai/skills | Skill | 2.6k | 4d ago | MIT | A | 113 | Claude Code, Codex |
| scroll-craftnateherkai/scroll-craft | Skill | 4.6k | 1mo ago | MIT | A | 177 | Claude Code |