design-agent

design-agent is a skill for Claude Code from sauravvarma/garage. It costs 186 tokens per session (6,732 once invoked), scanned A, original, MIT.

A design skill creates and critiques production design variants in Pencil, a design tool, within an already approved visual direction. It can also critique an existing design without creating a new one.

In plain words
What is it for?
Use it to design or critique pages in Pencil after the design direction is locked, including requests for an intentionally unconventional option.
Why use it?
It helps compare implementation-ready design options while keeping them aligned with the project's agreed visual direction.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the garage plugin — 6 skills, 1 hook shipped together

Good fit Use it to design or critique pages in Pencil after the design direction is locked, including requests for an intentionally unconventional option.

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

Made for: Claude Code.

Or install garage, the plugin that ships this one along with the rest of its 6 skills, 1 hook.

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-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sauravvarma/garage/design-agent"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/design-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,732 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 $0.00186 $0.06732
Opus 5 $0.00093 $0.03366
Sonnet 5 $0.00037 $0.01346
Haiku 4.5 $0.00019 $0.00673

Measured 9d ago against content hash a1a4c6716f18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-agent 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract-icon-paths.js, scripts/extract-mock-assets.py), 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.

skills/design-agent/SKILL.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Agent

An isolated design subagent that generates and critiques production design variants. Produces Pencil frames and structured critique reports. Explicit invocation only — never auto-triggered.

This skill is Mode B. When not invoked, Claude Code operates in Mode A (the confirmed human-orchestrated chain: spec-first → implement → visual QA → sync gate → commit). Mode B wraps Mode A by adding a design phase before implementation.

When to use

  • User explicitly says /design-agent "design the contact page" or similar
  • User says /design-agent "critique the home page frame" — critique-only mode
  • User says /design-agent "design X — include a wild one" — with pushed variant
  • Never auto-trigger on design-related conversation
  • Never suggest invoking this skill — wait for the user to invoke it

When NOT to use

  • User asks to implement something (Mode A)
  • User asks to fix a bug or adjust styling (Mode A)
  • User asks to run visual QA (use /visual-qa instead)
  • User wants to explore or discover a design direction (use /design-explore instead)
  • User wants to challenge or revisit locked design decisions (use /design-explore Mode 5)
  • Any task that doesn't start with explicit /design-agent invocation

Spec preflight

Before designing anything, verify the artifacts this skill depends on. Stop and present a checklist if anything required is missing — do not silently proceed with assumptions or invent values.

Required:

  • CLAUDE.md — project context, must contain a ## Pencil design file section with the absolute path to the .pen file
  • docs/BRIEF-AND-DIRECTION.md — tone, audience, goals
  • docs/DESIGN-LANGUAGE.md — typography, color, layout philosophy
  • docs/DESIGN-TOKENS.md — token values
  • docs/DESIGN-TAXONOMY.md — artifact index, frame naming convention
  • docs/DESIGN-HEURISTICS.md — taste settings (created by /design-explore)
  • docs/[FEATURE]-IDEAS.md — direction chosen + design variations for the feature being designed (created by /design-explore)

Read the full file on GitHub · 505 lines

Files

What ships with it

8 files 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.

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 · 505 lines · 186 tokens per session scan A a1a4c6716f18

Subscribe to this mod's changes

design-agent is a skill published in the GitHub repository sauravvarma/garage (3 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 6,732 once invoked, about $0.0009 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

extract-design

Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…

Manavarya09/design-extract · 98 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

system-pitch

Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…

murphytrueman/design-system-ops · 72 tokens

stakeholder-brief

Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…

murphytrueman/design-system-ops · 73 tokens

token-audit

Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…

murphytrueman/design-system-ops · 93 tokens

accessibility-per-component

Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…

murphytrueman/design-system-ops · 65 tokens