refs

refs is a skill for Claude Code from dkadts/landing-kit-building. It costs 58 tokens per session (1,760 once invoked), scanned A, original, MIT.

A design-reference reader that examines examples stored in a project and turns their shared visual patterns into design guidance and an approved checklist.

In plain words
What is it for?
Use it after the design brief is filled and references have been added. It creates a proposal for the design rules and a flat list of required visual elements.
Why use it?
It helps resolve clashes between references, such as a quiet mood paired with overly dramatic movement, before implementation. It also records which elements the user approved so later build and review work can enforce them.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after the design brief is filled and references have been added. It creates a proposal for the design rules and a flat list of required visual elements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dkadts/landing-kit-building/refs
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 dkadts/landing-kit-building --skill refs
Clone the repo
git clone --depth 1 https://github.com/dkadts/landing-kit-building

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 refs

README.md
[![agentmods](https://agentmods.dev/badge/skills/dkadts/landing-kit-building/refs.svg)](https://agentmods.dev/skills/dkadts/landing-kit-building/refs)
Your own site
<a href="https://agentmods.dev/skills/dkadts/landing-kit-building/refs"><img src="https://agentmods.dev/badge/skills/dkadts/landing-kit-building/refs.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,760 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 $0.00058 $0.01760
Opus 5 $0.00029 $0.00880
Sonnet 5 $0.00012 $0.00352
Haiku 4.5 $0.00006 $0.00176

Measured 7d ago against content hash 946a49b8156a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

refs 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 7d 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.

.claude/skills/refs/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/refs

Reads every folder under references/*/, extracts patterns per aspect, surfaces conflicts, and produces two artifacts:

  • references/proposal.md — recommendations for /design-lock.
  • references/approved-manifest.md — a flat list of required elements the user approved (see Step 5b).

When to use

  • After brief/05-design.md is filled.
  • The user placed references in references/.
  • Before /design-lock.

Requirements

  • At least 1 reference exists somewhere under references/*/.
  • brief/05-design.md is filled (mood, associations).

If no references at all — offer to base the design on brief/05-design.md and skip this skill.

Process

Step 1. Walk every aspect folder.

For each folder in references/:

  • animation/, structure/, typography/, color/, layout/, motion/, micro-interactions/, mood/, full-sites/
  • Read every subfolder: source.txt, notes.md, media files.
  • If the user provided a URL but no screenshot, WebFetch the visual/structure (do not pull code).

Step 2. Extract the common pattern per aspect.

For each aspect, articulate what's shared across references:

## animation
From 3 references:
- Common pattern: subtle scale-up on hover (1.02×), fade + slight lift on scroll
- Common ease: cubic-bezier(0.22, 1, 0.36, 1)
- Common duration: ~300ms
- Outlier: <linear-refs uses longer 500ms>

## typography
- Serif heading + sans body (2 of 3)
- Ratio ~1.333 (Perfect Fourth)
- Weights: 400 body, 700 headings — only two
- Heading line-height: 1.1 (tight, editorial)

Step 3. Detect conflicts.

Run through the pairs:

  • Mood vs Motion: "quiet luxury" + "bombastic scroll animations" → conflict.
  • Color vs Mood: "warm beige" + "neon accent" → conflict (unless neon is a declared subversion).
  • Density vs Typography: "compact" + "editorial serif big display" → conflict.
  • Density vs Structure: "editorial density" + "5+ sections" → conflict (editorial = fewer sections, more air).

Each conflict is a question to the user:

Read the full file on GitHub · 170 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. 7d ago First seen · 170 lines · 58 tokens per session scan A 946a49b8156a

Subscribe to this mod's changes

refs is a skill published in the GitHub repository dkadts/landing-kit-building (2 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 1,760 once invoked, about $0.0003 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

frontend-design

Visual and UX design quality for interfaces: hierarchy, spacing rhythm, typographic scale, a restrained color system, layout composition, and polished states. The taste layer above frontend architecture and a11y.

byerlikaya/claude-starter-kit · 44 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

agustinusnathaniel/nextarter-tailwind · 44 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

bravodev-hub/appointme · 90 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

agustinusnathaniel/nextarter-tailwind · 77 tokens

options

Present multiple design options as a vertical stack of anchored turns.

asgeirtj/system_prompts_leaks · 13 tokens

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

davila7/claude-code-templates · 34 tokens