design-playbooks

design-playbooks is a skill for Claude Code from veryCoolTimo/design-playbooks-skill. It costs 92 tokens per session (1,818 once invoked), scanned A, original, MIT.

A design reference library for coding agents, built from analyzed websites, design work, app icons, and share images. It provides examples and rules for page layouts, colors, typography, icons, and other visual choices.

In plain words
What is it for?
Use it when creating or editing a website interface, analyzing a live site, preparing DESIGN.md, or designing app icons and social-media share images.
Why use it?
It gives design work evidence and reusable references instead of relying only on personal taste. This helps an agent choose and document a coherent visual direction.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the design-playbooks plugin — 1 skill shipped together

Good fit Use it when creating or editing a website interface, analyzing a live site, preparing DESIGN.md, or designing app icons and social-media share images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verycooltimo/design-playbooks-skill/skill
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 veryCoolTimo/design-playbooks-skill --skill skill
Clone the repo
git clone --depth 1 https://github.com/veryCoolTimo/design-playbooks-skill

Made for: Claude Code.

Or install design-playbooks, the plugin that ships this one along with the rest of its 1 skill.

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 design-playbooks

README.md
[![agentmods](https://agentmods.dev/badge/skills/verycooltimo/design-playbooks-skill/skill/github.svg)](https://agentmods.dev/skills/verycooltimo/design-playbooks-skill/skill)
Your own site
<a href="https://agentmods.dev/skills/verycooltimo/design-playbooks-skill/skill"><img src="https://agentmods.dev/badge/skills/verycooltimo/design-playbooks-skill/skill/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 design-playbooks

Your own site · 80×15
<a href="https://agentmods.dev/skills/verycooltimo/design-playbooks-skill/skill"><img src="https://agentmods.dev/badge/skills/verycooltimo/design-playbooks-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,818 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 $0.00092 $0.01818
Opus 5 $0.00046 $0.00909
Sonnet 5 $0.00018 $0.00364
Haiku 4.5 $0.00009 $0.00182

Measured 9d ago against content hash 12c584c7d90d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-playbooks 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 9d 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.

skill/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design References & Intelligence

Library root: ~/.claude/design-library/ (call it $LIB). Machine index: $LIB/catalog.json (v2 — search it with scripts/find.py, don't hand-grep). Complements the official frontend-design skill: that one sets aesthetic direction; this one supplies evidence — real palettes, layouts, and rules synthesized from a corpus of 407 analyzed sites, 248 design works, 93 app icons, 49 OG images.

The corpus is a July-2026 snapshot; sites redesign. Trust the live URL over an old profile when they disagree, and offer to re-run Live Analyzer.

Routing — decide the task type first

Task Do
New page/site design Steps 1-5 below
Edit existing frontend Step 0 first, then 1-5
"Make DESIGN.md for my project / like " Generator (below)
Analyze a live URL Live Analyzer (below)
App icon Read $LIB/playbooks/domains/app-icons.md + $LIB/profiles/icons.md, view 3 refs from $LIB/media/app-icons/
OG / share image Read $LIB/playbooks/domains/og-images.md + $LIB/profiles/og.md, view 3 refs from $LIB/media/og-images/
Motion/branding/print inspiration grep $LIB/profiles/design.md by tag, view refs from $LIB/media/design/
"Show me references for X" Steps 1-3, present candidates with paths + URLs, stop

Style codes

ML=minimal-light · DT=dark-tech · DN=dark-neon · CP=colorful-playful · IL=illustration · BT=big-type · EL=elegant-serif · PH=photo-driven · GR=gradient-mesh Playbook file = $LIB/playbooks/styles/<full-name>.md (e.g. DT → dark-tech.md).

Valid filter values (use these exactly — don't invent):

  • category: developer-tools · ai-ml · productivity · design-creative · crypto-web3 · media-consumer · fintech · marketing-sales · hardware · health · data-analytics · ecommerce-retail · security · hr-people
  • tone: light · dark · page: home pricing blog product about resources solutions company features use-cases (others live in misc.md)

Core flow

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 92 tokens per session scan A 12c584c7d90d

Subscribe to this mod's changes

design-playbooks is a skill published in the GitHub repository veryCoolTimo/design-playbooks-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 1,818 once invoked, about $0.0005 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.