stitch-design

A design skill that turns rough interface ideas or visual references into a practical design-system specification.

In plain words
What is it for?
Use it to plan a new interface or translate an example design into implementable frontend guidance.
Why use it?
It gives developers defined colors, typography, spacing, components, and layout rules before UI work begins.

Skill for Claude CodeCodex

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/tjmustard/hypergraph-coding-agent-framework/hyper-stitch-design
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-stitch-design
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 618 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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00618
Opus 5 $0.00022 $0.00309
Sonnet 5 $0.00009 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 2d ago against content hash 7563c609a688, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stitch-design 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.

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.

.agents/skills/hyper-stitch-design/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch Design

This skill activates a UI/UX Designer and Frontend Specialist persona. It translates vague visual ideas ("make it look like this") into a concrete, implementable Design System and component specifications.

When to use this skill

  • When starting UI work for a new feature and needing a design spec.
  • When the user provides a visual reference ("make it look like X") and wants concrete tokens and components.
  • When the user explicitly runs /hyper-stitch-design.
  • Before handing UI work to a Builder agent that needs precise visual specs.

How to use it

Inputs

  • User prompt describing the desired aesthetic (e.g., "Modern SaaS dashboard", "Brutalist e-commerce").
  • Optional: reference image or URL for style extraction.
  • spec/compiled/SuperPRD.md or MiniPRD_*.md for functional requirements.

Step 1: Analyze the Aesthetic

  • Identify the desired visual style (e.g., Modern, Brutalist, Corporate, Minimalist).

  • If a reference image is provided, extract: color palette, typography, spacing rhythm, and shadow usage.

  • If no reference is provided, use AskUserQuestion:

    What design style or reference are we targeting?
    
    - Option A: Provide a reference URL — paste a site URL you want to emulate
    - Option B: Use a style keyword — describe the aesthetic (e.g., minimal, brutalist, glassmorphism)
    - Option C: Match existing codebase — derive the design system from existing UI files
    

Step 2: Define the Design System

Create or update docs/DESIGN.md with:

Tokens:

  • Primary/secondary/accent colors (hex + semantic name)
  • Neutral scale (background, surface, border, text)
  • Spacing scale (4px base unit or equivalent)
  • Font stack (headings, body, mono)
  • Shadow levels (none, sm, md, lg)
  • Border radius scale

Components:

  • Specify visual states for core elements: buttons (default, hover, active, disabled, loading), inputs (default, focus, error), cards, badges, modals.

Layout:

  • Grid system (columns, gutters)
  • Responsive breakpoints
  • Container max-widths

Read the full file on GitHub · 62 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. 2d ago First seen · 62 lines · 43 tokens per session scan A 7563c609a688

Subscribe to this mod's changes

stitch-design is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 618 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 2026-08-31.

Related

Other skills, from other repositories

i18n-localization

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

vudovn/ag-kit · 27 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

harden

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.

childrentime/reactuse · 32 tokens

iflytek-text-proofread

Proofread Chinese text using iFlytek's Official Document Proofreading API (公文校对). Detects 27 types of errors across three categories.

iflytek/iFly-Skills · 88 tokens

a11y-remediate

Use to produce a leader-facing remediation proposal from one or more /a11y-audit outputs plus team and product context. Translates audit findings into sprint plans, staffing asks, customer-facing language, compliance rollups, and critical-path analysis. Refuses to fabricate numbers, owners, or commitments beyond the…

gitkraken/vscode-gitlens · 72 tokens